DokuWiki

<h1>Stage M1R 2017</h1>
<div class="level1">

</div>

<h2>Pointeurs</h2>
<div class="level2">

</div>

<h4>RL</h4>
<div class="level4">
<ul>
<li class="level1"> cours M1:  <a href="/lib/exe/fetch.php?media=m1r2017:cm1m22016-17.pdf" class="media mediafile mf_pdf" title="m1r2017:cm1m22016-17.pdf (6.6 MB)">MDP et planif</a>, <a href="/lib/exe/fetch.php?media=m1r2017:cm4a2016rl.pdf" class="media mediafile mf_pdf" title="m1r2017:cm4a2016rl.pdf (9.3 MB)">RL</a>  </li>
<li class="level1"> cours David Silver : http://www0.cs.ucl.ac.uk/staff/D.Silver/web/Teaching.html</li>
<li class="level1"> livre de Sutton mis à jour:  https://webdocs.cs.ualberta.ca/~sutton/book/bookdraft2016sep.pdf</li>
</ul>
<ul>
<li class="level1 node"> Multi-Agent RL : <ul>
<li class="level3"> en premier, lire le chapitre 4 de https://tel.archives-ouvertes.fr/file/index/docid/362529/filename/these_matignon.pdf</li>
<li class="level3"> puis lire http://liris.cnrs.fr/laetitia.matignon/index/matignon2012KER.pdf</li>
</ul>
</li>
</ul>
<ul>
<li class="level1 node"> Travaux de De Hauwere: Learning multi-agent state space representations<ul>
<li class="level3"> http://www.aamas-conference.org/Proceedings/aamas2010/pdf/01%20Full%20Papers/15_02_FP_0421.pdf</li>
<li class="level3"> https://ai.vub.ac.be/ALA2012/downloads/paper5.pdf</li>
</ul>
</li>
</ul>

</div>

<h4>Construction de représentations en RL</h4>
<div class="level4">
<ul>
<li class="level1"> Tile Coding et versions adaptatives <a href="/lib/exe/fetch.php?tok=2f96da&media=http%3A%2F%2Fwww.cs.utexas.edu%2F~ai-lab%2Fpubs%2Fwhitesontr07.ps" class="media mediafile mf_ps" title="http://www.cs.utexas.edu/~ai-lab/pubs/whitesontr07.ps">adaptative_tile_coding [Whiteson,2007] </a> et <a href="/lib/exe/fetch.php?tok=3e2a76&media=http%3A%2F%2Fwww.aaai.org%2Focs%2Findex.php%2FWS%2FAAAIW10%2Fpaper%2FviewFile%2F2068%2F2422" class="media mediafile mf_php_ws_aaaiw10_paper_viewfile_2068_2422" title="http://www.aaai.org/ocs/index.php/WS/AAAIW10/paper/viewFile/2068/2422">evolutionary_tile_coding [Lin,2010] </a></li>
<li class="level1"> Combinaison de growing neural gaz GNG et Q-Learning pour discrétisation adaptative de l'espace d'états: http:<em>liris.cnrs.fr/sasem/lib/exe/fetch.php?media=m1r2017:vieira2013tdgngoriginal.pdf
  * <a href="/lib/exe/fetch.php?tok=eac757&media=http%3A%2F%2Fnn.cs.utexas.edu%2Fdownloads%2Fpapers%2Fprovost.connsci06.pdf" class="media mediafile mf_pdf" title="http://nn.cs.utexas.edu/downloads/papers/provost.connsci06.pdf">Self-Organizing Distinctive-State Abstraction (SODA) [Kuipers,2006] </a>

=== App Constructiviste ===
  * Thèse S. Mazac: https://tel.archives-ouvertes.fr/tel-01310583/file/TH2015MazacSebastien.pdf

=== RL et Inspirations Constructivistes ===
   * Intrinsically Motivated RL [Singh2005] https://web.eecs.umich.edu/~baveja/Papers/FinalNIPSIMRL.pdf

===== Mémentos  =====

A lire : 
   * https:</em>ai.vub.ac.be/ALA2012/downloads/paper4.pdf</li>
<li class="level1"> http:<em>ir.library.oregonstate.edu/xmlui/bitstream/handle/1957/39192/HolmesParkerChristopherG2013.pdf;sequence=1
==== App Constructiviste ====
   * <a href="/doku.php?id=compte-rendu-etat-art-these" class="wikilink1" title="compte-rendu-etat-art-these" data-wiki-id="compte-rendu-etat-art-these"> Etat de l'art (Thèse S. Mazac)</a>

==== RL ====
=== Multi-agents ===
   * <a href="/doku.php?id=memento-learning-multi-agent-state-space-representations" class="wikilink1" title="memento-learning-multi-agent-state-space-representations" data-wiki-id="memento-learning-multi-agent-state-space-representations"> Learning multi-agent state space representations (CQLearning)</a>
   * <a href="/doku.php?id=memento-processus-decisionnels-de-markov-et-systemes-multiagents" class="wikilink1" title="memento-processus-decisionnels-de-markov-et-systemes-multiagents" data-wiki-id="memento-processus-decisionnels-de-markov-et-systemes-multiagents"> Processus décisionnels de Markov et systèmes multiagents (Thèse L. Matignon)</a>
   * <a href="/doku.php?id=memento-independent-reinforcement-learners-cooperative-markov-games:a-survey-regarding-coordination-problems" class="wikilink1" title="memento-independent-reinforcement-learners-cooperative-markov-games:a-survey-regarding-coordination-problems" data-wiki-id="memento-independent-reinforcement-learners-cooperative-markov-games:a-survey-regarding-coordination-problems"> Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems</a>
   * <a href="/doku.php?id=memento-context-sensitive-reward-shaping-for-sparse-inter-action-multi-agent-systems" class="wikilink1" title="memento-context-sensitive-reward-shaping-for-sparse-inter-action-multi-agent-systems" data-wiki-id="memento-context-sensitive-reward-shaping-for-sparse-inter-action-multi-agent-systems"> Context-Sensitive Reward Shaping for Sparse Inter-action Multi-Agent Systems</a>

=== Inspirations Constructivistes ===
   * <a href="/doku.php?id=memento-intrinsically-motivated-rl" class="wikilink1" title="memento-intrinsically-motivated-rl" data-wiki-id="memento-intrinsically-motivated-rl"> Intrinsically Motivated RL [Singh2005]</a>

==== Value function approximation ====
   * <a href="/doku.php?id=memento-value-function-approximation" class="wikilink1" title="memento-value-function-approximation" data-wiki-id="memento-value-function-approximation"> Quelques infos</a>

==== Temporal Difference - Growing Neural Gas ====
   * <a href="/doku.php?id=memento-td-gng" class="wikilink1" title="memento-td-gng" data-wiki-id="memento-td-gng"> TD-GNG</a>

===== Réflexions  =====
   * <a href="/doku.php?id=reflexion-gng-qc" class="wikilink1" title="reflexion-gng-qc" data-wiki-id="reflexion-gng-qc"> CQ-Learning et TD-GNG</a>

===== Comptes-rendu de réunion  =====

Dossier contenant les slides présentés lors des réunions :
 slides

* <a href="/doku.php?id=reu02-03-17" class="wikilink1" title="reu02-03-17" data-wiki-id="reu02-03-17">02/03/17</a>
   * <a href="/doku.php?id=reu14-03-17" class="wikilink1" title="reu14-03-17" data-wiki-id="reu14-03-17">14/03/17</a>
   * <a href="/doku.php?id=reu24-03-17" class="wikilink1" title="reu24-03-17" data-wiki-id="reu24-03-17">24/03/17</a>
</li>
</ul>

</div>

Enable Complex Tables Editor Height px Turn supplementary image paste support on

Edit summary: Minor changes

Please fill all the letters into the box to prove you're human. F S O V Q Please keep this field empty:

DokuWiki

Site Tools

Page Tools