https://learnlab.org/wiki/index.php?title=Chi_-_Induction_of_Adaptive_Pedagogical_Tutorial_Tactics&feed=atom&action=historyChi - Induction of Adaptive Pedagogical Tutorial Tactics - Revision history2024-03-28T14:27:53ZRevision history for this page on the wikiMediaWiki 1.31.12https://learnlab.org/wiki/index.php?title=Chi_-_Induction_of_Adaptive_Pedagogical_Tutorial_Tactics&diff=11086&oldid=prevKoedinger: Undo revision 11063 by Fa11 (Talk)2010-10-07T11:07:14Z<p>Undo revision 11063 by <a href="/wiki/index.php?title=Special:Contributions/Fa11" title="Special:Contributions/Fa11">Fa11</a> (<a href="/wiki/index.php?title=User_talk:Fa11&action=edit&redlink=1" class="new" title="User talk:Fa11 (page does not exist)">Talk</a>)</p>
<table class="diff diff-contentalign-left" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 11:07, 7 October 2010</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l9" >Line 9:</td>
<td colspan="2" class="diff-lineno">Line 9:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Previously, we applied MDPs model to induce pedagogical policies from the data. However, a framework more suitable for this task is the Partially Observable Markov Decision Process (POMDP).  POMDPs allow for realistic modeling of the students’ knowledge levels, the students’ intentions, and other hidden state components by incorporating them into the state space.  POMDPs explicitly represent two sources of uncertainty: non-determinism in the control process and partial observability of the students’ knowledge levels.  In the former case, outcomes of the tutorial actions or students’ knowledge level are not deterministic; in the latter, the underlying students’ knowledge levels are observed indirectly via incomplete or imperfect observations. The goal of year 6 is to explore the use of POMDP models.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Previously, we applied MDPs model to induce pedagogical policies from the data. However, a framework more suitable for this task is the Partially Observable Markov Decision Process (POMDP).  POMDPs allow for realistic modeling of the students’ knowledge levels, the students’ intentions, and other hidden state components by incorporating them into the state space.  POMDPs explicitly represent two sources of uncertainty: non-determinism in the control process and partial observability of the students’ knowledge levels.  In the former case, outcomes of the tutorial actions or students’ knowledge level are not deterministic; in the latter, the underlying students’ knowledge levels are observed indirectly via incomplete or imperfect observations. The goal of year 6 is to explore the use of POMDP models.</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del style="font-weight: bold; text-decoration: none;">[http://www.ny-liability-insurance.com/ general liability insurance ny]</del></div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Integrated Research Results and High Profile Publication ==</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Integrated Research Results and High Profile Publication ==</div></td></tr>
</table>Koedingerhttps://learnlab.org/wiki/index.php?title=Chi_-_Induction_of_Adaptive_Pedagogical_Tutorial_Tactics&diff=11063&oldid=prevFa11 at 21:06, 22 September 20102010-09-22T21:06:21Z<p></p>
<table class="diff diff-contentalign-left" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 21:06, 22 September 2010</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l9" >Line 9:</td>
<td colspan="2" class="diff-lineno">Line 9:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Previously, we applied MDPs model to induce pedagogical policies from the data. However, a framework more suitable for this task is the Partially Observable Markov Decision Process (POMDP).  POMDPs allow for realistic modeling of the students’ knowledge levels, the students’ intentions, and other hidden state components by incorporating them into the state space.  POMDPs explicitly represent two sources of uncertainty: non-determinism in the control process and partial observability of the students’ knowledge levels.  In the former case, outcomes of the tutorial actions or students’ knowledge level are not deterministic; in the latter, the underlying students’ knowledge levels are observed indirectly via incomplete or imperfect observations. The goal of year 6 is to explore the use of POMDP models.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Previously, we applied MDPs model to induce pedagogical policies from the data. However, a framework more suitable for this task is the Partially Observable Markov Decision Process (POMDP).  POMDPs allow for realistic modeling of the students’ knowledge levels, the students’ intentions, and other hidden state components by incorporating them into the state space.  POMDPs explicitly represent two sources of uncertainty: non-determinism in the control process and partial observability of the students’ knowledge levels.  In the former case, outcomes of the tutorial actions or students’ knowledge level are not deterministic; in the latter, the underlying students’ knowledge levels are observed indirectly via incomplete or imperfect observations. The goal of year 6 is to explore the use of POMDP models.</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">[http://www.ny-liability-insurance.com/ general liability insurance ny]</ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Integrated Research Results and High Profile Publication ==</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Integrated Research Results and High Profile Publication ==</div></td></tr>
</table>Fa11https://learnlab.org/wiki/index.php?title=Chi_-_Induction_of_Adaptive_Pedagogical_Tutorial_Tactics&diff=10986&oldid=prevChimingirl: /* Integrated Research Results and High Profile Publication */2010-08-31T21:27:38Z<p><span dir="auto"><span class="autocomment">Integrated Research Results and High Profile Publication</span></span></p>
<table class="diff diff-contentalign-left" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 21:27, 31 August 2010</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l29" >Line 29:</td>
<td colspan="2" class="diff-lineno">Line 29:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>durationKCBetweenDecisionT: a Temporal Situation feature which represents the time since the last tutorial decision was made on the current KC.   </div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>durationKCBetweenDecisionT: a Temporal Situation feature which represents the time since the last tutorial decision was made on the current KC.   </div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">Currently, we are working on exploring the use of POMDP models.  More specifically, we have defined preliminary structures of the POMDP and selected a training corpus that can be used to learn the POMDP.  The selected structure for POMDP is knowledge tracing and Additive Factor Model (AFM).  We also want to investigate how certain factors would impact the effectiveness of the induced tutorial tactics and these factors include (1) the choice of Training Corpus, (2) the choice of the state modeling and representation, and (3) the choice of the reward functions and so on. </ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">Additionally, we have been worked on investigating the causes of the effectiveness of the induced pedagogical tactics in the previous study by applying learning decomposition.  We want to compare the RL-induced tutorial tactics with pre-existing learning theory, such as zone of proximal development (ZPD) (Vygotsky; 1978) and assistant dilemma (Koedinger et al. 2008) and so on.</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=== Publications:===</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=== Publications:===</div></td></tr>
</table>Chimingirlhttps://learnlab.org/wiki/index.php?title=Chi_-_Induction_of_Adaptive_Pedagogical_Tutorial_Tactics&diff=10985&oldid=prevChimingirl: /* Publications: */2010-08-31T21:26:26Z<p><span dir="auto"><span class="autocomment">Publications:</span></span></p>
<table class="diff diff-contentalign-left" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 21:26, 31 August 2010</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l33" >Line 33:</td>
<td colspan="2" class="diff-lineno">Line 33:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Chi, M., Vanlehn, K., Litman, D (2010a). The More the Merrier? Examining Three Interaction Hypotheses. Proceedings of the 32nd Annual Conference of the Cognitive Science Society (CogSci2010), Portland, Oregon.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Chi, M., Vanlehn, K., Litman, D (2010a). The More the Merrier? Examining Three Interaction Hypotheses. Proceedings of the 32nd Annual Conference of the Cognitive Science Society (CogSci2010), Portland, Oregon.</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Chi, M. VanLehn, K., and Litman, D. (2010b). Do Micro-Level Tutorial Decisions Matter: Applying Reinforcement Learning To Induce Pedagogical Tutorial Tactics. Proceedings 10th International Conference on Intelligent Tutoring Systems (ITS2010) (pp 224-234).</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Chi, M. VanLehn, K., and Litman, D. (2010b). Do Micro-Level Tutorial Decisions Matter: Applying Reinforcement Learning To Induce Pedagogical Tutorial Tactics. Proceedings 10th International Conference on Intelligent Tutoring Systems (ITS2010) (pp 224-234).</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Chi, M. VanLehn, K. Litman, D., and Jordan, P. (2010c). Inducing Effective Pedagogical Strategies Using Learning Context Features. Proceedings Eighteenth International Conference on User Modeling, Adaptation, and Personalization (UMAP2010). (pp 147-158).</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Chi, M. VanLehn, K. Litman, D., and Jordan, P. (2010c). Inducing Effective Pedagogical Strategies Using Learning Context Features. Proceedings Eighteenth International Conference on User Modeling, Adaptation, and Personalization (UMAP2010). (pp 147-158).</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>•  Chi, M., Vanlehn, K., Litman, D, and  Jordan, P. (Accept upon revisions). Empirically Evaluating the Application of Reinforcement Learning to the Induction of Effective Pedagogical Tactics.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>•  Chi, M., Vanlehn, K., Litman, D, and  Jordan, P. (Accept upon revisions). Empirically Evaluating the Application of Reinforcement Learning to the Induction of Effective Pedagogical Tactics.</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del style="font-weight: bold; text-decoration: none;"></del></div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=== Year 6 Project Deliverables ===</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=== Year 6 Project Deliverables ===</div></td></tr>
</table>Chimingirlhttps://learnlab.org/wiki/index.php?title=Chi_-_Induction_of_Adaptive_Pedagogical_Tutorial_Tactics&diff=10984&oldid=prevChimingirl: /* Integrated Research Results and High Profile Publication */2010-08-31T21:26:11Z<p><span dir="auto"><span class="autocomment">Integrated Research Results and High Profile Publication</span></span></p>
<table class="diff diff-contentalign-left" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 21:26, 31 August 2010</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l30" >Line 30:</td>
<td colspan="2" class="diff-lineno">Line 30:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>durationKCBetweenDecisionT: a Temporal Situation feature which represents the time since the last tutorial decision was made on the current KC.   </div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>durationKCBetweenDecisionT: a Temporal Situation feature which represents the time since the last tutorial decision was made on the current KC.   </div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>Publications:</div></td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins class="diffchange diffchange-inline">=== </ins>Publications:<ins class="diffchange diffchange-inline">===</ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Chi, M., Vanlehn, K., Litman, D (2010a). The More the Merrier? Examining Three Interaction Hypotheses. Proceedings of the 32nd Annual Conference of the Cognitive Science Society (CogSci2010), Portland, Oregon.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Chi, M., Vanlehn, K., Litman, D (2010a). The More the Merrier? Examining Three Interaction Hypotheses. Proceedings of the 32nd Annual Conference of the Cognitive Science Society (CogSci2010), Portland, Oregon.</div></td></tr>
</table>Chimingirlhttps://learnlab.org/wiki/index.php?title=Chi_-_Induction_of_Adaptive_Pedagogical_Tutorial_Tactics&diff=10983&oldid=prevChimingirl: /* Integrated Research Results and High Profile Publication */2010-08-31T21:25:45Z<p><span dir="auto"><span class="autocomment">Integrated Research Results and High Profile Publication</span></span></p>
<table class="diff diff-contentalign-left" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 21:25, 31 August 2010</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l30" >Line 30:</td>
<td colspan="2" class="diff-lineno">Line 30:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>durationKCBetweenDecisionT: a Temporal Situation feature which represents the time since the last tutorial decision was made on the current KC.   </div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>durationKCBetweenDecisionT: a Temporal Situation feature which represents the time since the last tutorial decision was made on the current KC.   </div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">Publications:</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">Chi, M., Vanlehn, K., Litman, D (2010a). The More the Merrier? Examining Three Interaction Hypotheses. Proceedings of the 32nd Annual Conference of the Cognitive Science Society (CogSci2010), Portland, Oregon.</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">Chi, M. VanLehn, K., and Litman, D. (2010b). Do Micro-Level Tutorial Decisions Matter: Applying Reinforcement Learning To Induce Pedagogical Tutorial Tactics. Proceedings 10th International Conference on Intelligent Tutoring Systems (ITS2010) (pp 224-234).</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">Chi, M. VanLehn, K. Litman, D., and Jordan, P. (2010c). Inducing Effective Pedagogical Strategies Using Learning Context Features. Proceedings Eighteenth International Conference on User Modeling, Adaptation, and Personalization (UMAP2010). (pp 147-158).</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">•  Chi, M., Vanlehn, K., Litman, D, and  Jordan, P. (Accept upon revisions). Empirically Evaluating the Application of Reinforcement Learning to the Induction of Effective Pedagogical Tactics.</ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
</table>Chimingirlhttps://learnlab.org/wiki/index.php?title=Chi_-_Induction_of_Adaptive_Pedagogical_Tutorial_Tactics&diff=10982&oldid=prevChimingirl: /* Integrated Research Results and High Profile Publication */2010-08-31T21:24:22Z<p><span dir="auto"><span class="autocomment">Integrated Research Results and High Profile Publication</span></span></p>
<table class="diff diff-contentalign-left" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 21:24, 31 August 2010</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l19" >Line 19:</td>
<td colspan="2" class="diff-lineno">Line 19:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Compared with previous research on applying RL to induce pedagogical policies on ITSs, this project so far has at least two major contributions. First, we showed that using a relatively small exploratory corpus as training corpus for inducing pedagogical policies is a feasible approach. Second, we empirically showed that the RL induced policies indeed made students learn deeper or better.  </div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Compared with previous research on applying RL to induce pedagogical policies on ITSs, this project so far has at least two major contributions. First, we showed that using a relatively small exploratory corpus as training corpus for inducing pedagogical policies is a feasible approach. Second, we empirically showed that the RL induced policies indeed made students learn deeper or better.  </div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>Moreover, while much of previous research on applying RL to ITSs and non-tutoring NL Dialogue systems used pre-defined state representation,  our approach in this project is to begin with a large set of features to which a series of feature-selection methods were applied to reduce them to a tractable subset. <del class="diffchange diffchange-inline">In this paper</del>, we <del class="diffchange diffchange-inline">will </del>shed some lights on the relative effectiveness of different feature selection methods and which features among the ones defined were most involved in the final induced policies.</div></td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>Moreover, while much of previous research on applying RL to ITSs and non-tutoring NL Dialogue systems used pre-defined state representation,  our approach in this project is to begin with a large set of features to which a series of feature-selection methods were applied to reduce them to a tractable subset. <ins class="diffchange diffchange-inline">By doing log analysis</ins>, we shed some lights on the relative effectiveness of different feature selection methods and which features among the ones defined were most involved in the final induced policies.</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>The most frequent features appeared in the <del class="diffchange diffchange-inline">NormGain </del>policies are:</div></td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>The most frequent features appeared in the <ins class="diffchange diffchange-inline">induced </ins>policies <ins class="diffchange diffchange-inline">employed by the Experimental group </ins>are:</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>StepDifficultyPS: a Problem Solving Contextual feature which encodes a step's difficulty level and its value is roughly estimated from the Combined Corpus based on the percentage of answers that were correct on the step.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>StepDifficultyPS: a Problem Solving Contextual feature which encodes a step's difficulty level and its value is roughly estimated from the Combined Corpus based on the percentage of answers that were correct on the step.</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
</table>Chimingirlhttps://learnlab.org/wiki/index.php?title=Chi_-_Induction_of_Adaptive_Pedagogical_Tutorial_Tactics&diff=10981&oldid=prevChimingirl: /* Integrated Research Results and High Profile Publication */2010-08-31T21:22:59Z<p><span dir="auto"><span class="autocomment">Integrated Research Results and High Profile Publication</span></span></p>
<table class="diff diff-contentalign-left" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 21:22, 31 August 2010</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l17" >Line 17:</td>
<td colspan="2" class="diff-lineno">Line 17:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Moreover, the pedagogical policies employed by the Experimental group were derived from the log files from two pre-existing training corpora. Since the Experimental Group experienced the identical procedure and training materials as the students collected in the pre-existing training corpora, a post-hoc comparison was done among the three groups.  Results showed that while no significant differences were found on pre-test score and time on training among the three groups, there were significant differences among the three groups on both post-test scores and NLG scores:  F(2, 127) = 5.16, p = 0.007 and F(2, 127) = 7.57, p = 0.001 respectively (Chi et al., 2010b).  More specifically, the Experimental Group significantly out-performed the two previous groups in terms of posttest scores and NLG. This result suggested that RL can be fruitfully applied to induce more effective, adaptive pedagogical strategies from less effective pre-existing data.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Moreover, the pedagogical policies employed by the Experimental group were derived from the log files from two pre-existing training corpora. Since the Experimental Group experienced the identical procedure and training materials as the students collected in the pre-existing training corpora, a post-hoc comparison was done among the three groups.  Results showed that while no significant differences were found on pre-test score and time on training among the three groups, there were significant differences among the three groups on both post-test scores and NLG scores:  F(2, 127) = 5.16, p = 0.007 and F(2, 127) = 7.57, p = 0.001 respectively (Chi et al., 2010b).  More specifically, the Experimental Group significantly out-performed the two previous groups in terms of posttest scores and NLG. This result suggested that RL can be fruitfully applied to induce more effective, adaptive pedagogical strategies from less effective pre-existing data.</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>Compared with previous <del class="diffchange diffchange-inline">studies </del>on applying RL to induce pedagogical policies on ITSs, this project so far has at least two major contributions. First, we showed that using a relatively small exploratory corpus as training corpus for inducing pedagogical policies is a feasible approach. Second, we empirically showed that the RL induced policies indeed made students learn deeper or better.  </div></td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>Compared with previous <ins class="diffchange diffchange-inline">research </ins>on applying RL to induce pedagogical policies on ITSs, this project so far has at least two major contributions. First, we showed that using a relatively small exploratory corpus as training corpus for inducing pedagogical policies is a feasible approach. Second, we empirically showed that the RL induced policies indeed made students learn deeper or better.  </div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Moreover, while much of previous research on applying RL to ITSs and non-tutoring NL Dialogue systems used pre-defined state representation,  our approach in this project is to begin with a large set of features to which a series of feature-selection methods were applied to reduce them to a tractable subset. In this paper, we will shed some lights on the relative effectiveness of different feature selection methods and which features among the ones defined were most involved in the final induced policies.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Moreover, while much of previous research on applying RL to ITSs and non-tutoring NL Dialogue systems used pre-defined state representation,  our approach in this project is to begin with a large set of features to which a series of feature-selection methods were applied to reduce them to a tractable subset. In this paper, we will shed some lights on the relative effectiveness of different feature selection methods and which features among the ones defined were most involved in the final induced policies.</div></td></tr>
</table>Chimingirlhttps://learnlab.org/wiki/index.php?title=Chi_-_Induction_of_Adaptive_Pedagogical_Tutorial_Tactics&diff=10980&oldid=prevChimingirl: /* Planned accomplishments for PSLC Year 6 */2010-08-31T21:22:24Z<p><span dir="auto"><span class="autocomment">Planned accomplishments for PSLC Year 6</span></span></p>
<table class="diff diff-contentalign-left" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 21:22, 31 August 2010</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l8" >Line 8:</td>
<td colspan="2" class="diff-lineno">Line 8:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Planned accomplishments for PSLC Year 6 ==</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Planned accomplishments for PSLC Year 6 ==</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>Previously, we applied MDPs model to induce pedagogical policies from the data. However, a framework more suitable for this task is the Partially Observable Markov Decision Process (POMDP).  POMDPs allow for realistic modeling of the students’ knowledge levels, the students’ intentions, and other hidden state components by incorporating them into the state space.  POMDPs explicitly represent two sources of uncertainty: non-determinism in the control process and partial observability of the students’ knowledge levels.  In the former case, outcomes of the tutorial actions or students’ knowledge level are not deterministic; in the latter, the underlying students’ knowledge levels are observed indirectly via incomplete or imperfect observations. The goal of year 6 is to explore the use of POMDP models<del class="diffchange diffchange-inline">. Additionally, we have been worked on investigating the causes of the effectiveness of the induced pedagogical tactics in the previous study</del>.</div></td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>Previously, we applied MDPs model to induce pedagogical policies from the data. However, a framework more suitable for this task is the Partially Observable Markov Decision Process (POMDP).  POMDPs allow for realistic modeling of the students’ knowledge levels, the students’ intentions, and other hidden state components by incorporating them into the state space.  POMDPs explicitly represent two sources of uncertainty: non-determinism in the control process and partial observability of the students’ knowledge levels.  In the former case, outcomes of the tutorial actions or students’ knowledge level are not deterministic; in the latter, the underlying students’ knowledge levels are observed indirectly via incomplete or imperfect observations. The goal of year 6 is to explore the use of POMDP models.</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Integrated Research Results and High Profile Publication ==</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Integrated Research Results and High Profile Publication ==</div></td></tr>
</table>Chimingirlhttps://learnlab.org/wiki/index.php?title=Chi_-_Induction_of_Adaptive_Pedagogical_Tutorial_Tactics&diff=10979&oldid=prevChimingirl: /* Integrated Research Results and High Profile Publication */2010-08-31T21:14:27Z<p><span dir="auto"><span class="autocomment">Integrated Research Results and High Profile Publication</span></span></p>
<table class="diff diff-contentalign-left" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="en">
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td>
<td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 21:14, 31 August 2010</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l23" >Line 23:</td>
<td colspan="2" class="diff-lineno">Line 23:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The most frequent features appeared in the NormGain policies are:</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The most frequent features appeared in the NormGain policies are:</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>StepDifficultyPS: a Problem Solving Contextual feature which encodes a step's difficulty level and its value is roughly estimated from the Combined Corpus based on the percentage of answers that were correct on the step.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>StepDifficultyPS: a Problem Solving Contextual feature which encodes a step's difficulty level and its value is roughly estimated from the Combined Corpus based on the percentage of answers that were correct on the step.</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>tutConceptsToWordsPS: a Problem Solving Contextual feature which represents the ratio of the physics concepts to words in the tutor's dialogue.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>tutConceptsToWordsPS: a Problem Solving Contextual feature which represents the ratio of the physics concepts to words in the tutor's dialogue.</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>tellsSinceElicitA: an Autonomy feature which represents the number of tells the student has received since the last elicit.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>tellsSinceElicitA: an Autonomy feature which represents the number of tells the student has received since the last elicit.</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>durationKCBetweenDecisionT: a Temporal Situation feature which represents the time since the last tutorial decision was made on the current KC.   </div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>durationKCBetweenDecisionT: a Temporal Situation feature which represents the time since the last tutorial decision was made on the current KC.   </div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l30" >Line 30:</td>
<td colspan="2" class="diff-lineno">Line 33:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=== Year 6 Project Deliverables ===</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=== Year 6 Project Deliverables ===</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del class="diffchange diffchange-inline">* Develop code and human-computer interfaces for applying</del>, <del class="diffchange diffchange-inline">comparing and interpreting cognitive model discovery algorithms across multiple data sets </del>in <del class="diffchange diffchange-inline">DataShop.  </del></div></td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins class="diffchange diffchange-inline">Year 6 Project Deliverable</ins></div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del class="diffchange diffchange-inline">* Demonstrate the use </del>of the <del class="diffchange diffchange-inline">model discovery infrastructure for at least two discovery algorithms applied to at least 4 DataShop data sets</del>.  </div></td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins class="diffchange diffchange-inline">1. 1) A selection of POMDP policies</ins>, <ins class="diffchange diffchange-inline">beginning with the ones </ins>in <ins class="diffchange diffchange-inline">step 3 </ins>of the <ins class="diffchange diffchange-inline">6th month milestones</ins>.</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del class="diffchange diffchange-inline">* For at least one of </del>these <del class="diffchange diffchange-inline">data sets, work with associated researchers to perform a “close the loop” experiment whereby we test that a better cognitive model leads to better or more efficient student learning</del>. <del class="diffchange diffchange-inline"> </del></div></td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins class="diffchange diffchange-inline">2. 2) Explore different ways to evaluate </ins>these <ins class="diffchange diffchange-inline">POMDP policies</ins>.</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div> </div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=== 6th Month Milestone ===</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=== 6th Month Milestone ===</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>By <del class="diffchange diffchange-inline">March</del>, 2010 we will 1<del class="diffchange diffchange-inline">) be able to run the LFA algorithm </del>on <del class="diffchange diffchange-inline">PSLC data sets from </del>the <del class="diffchange diffchange-inline">DataShop web services</del>, <del class="diffchange diffchange-inline">2) have run model discovery with using at least one algorithm on at least two data sets</del>, and <del class="diffchange diffchange-inline">3) we will have designed and ideally run the close-the-loop experiment</del>.</div></td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>By <ins class="diffchange diffchange-inline">May 1st (Min Chi starts Nov 1)</ins>, 2010 we will</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>1<ins class="diffchange diffchange-inline">. Extract initial features & explore use of additional features based </ins>on <ins class="diffchange diffchange-inline">knowledge tracing and detectors of affect and motivation.</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins class="diffchange diffchange-inline">2. Design initial POMDP models</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins class="diffchange diffchange-inline">3. Derive initial policies by exploring </ins>the <ins class="diffchange diffchange-inline">impact of different corpora</ins>, <ins class="diffchange diffchange-inline">different feature selection or extraction approaches, clustering methods</ins>, and <ins class="diffchange diffchange-inline">so on</ins>.</div></td></tr>
</table>Chimingirl