====== Stage M1R 2017 ======



===== Pointeurs  =====

=== RL ===
  * cours M1:  {{m1r2017:cm1m22016-17.pdf|MDP et planif}}, {{m1r2017:cm4a2016rl.pdf|RL}}  
  * cours David Silver : [[http://www0.cs.ucl.ac.uk/staff/D.Silver/web/Teaching.html]]
  * livre de Sutton mis à jour:  [[https://webdocs.cs.ualberta.ca/~sutton/book/bookdraft2016sep.pdf]]

  * Multi-Agent RL : 
      * en premier, lire le chapitre 4 de [[https://tel.archives-ouvertes.fr/file/index/docid/362529/filename/these_matignon.pdf]]
      * puis lire [[http://liris.cnrs.fr/laetitia.matignon/index/matignon2012KER.pdf]]
 
  * Travaux de De Hauwere: Learning multi-agent state space representations
      * [[http://www.aamas-conference.org/Proceedings/aamas2010/pdf/01%20Full%20Papers/15_02_FP_0421.pdf]]
      * [[https://ai.vub.ac.be/ALA2012/downloads/paper5.pdf]]
   

=== 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  =====

==== App Constructiviste ====
   * [[compte-rendu-etat-art-these | Etat de l'art (Thèse S. Mazac)]]

==== RL ====
=== Multi-agents ===
   * [[memento-Learning-multi-agent-state-space-representations | Learning multi-agent state space representations (CQLearning)]]
   * [[memento-Processus-décisionnels-de-Markov-et-systèmes-multiagents | Processus décisionnels de Markov et systèmes multiagents (Thèse L. Matignon)]]
   * [[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 terminer)]]
   * [[memento-Context-Sensitive-Reward-Shaping-for-Sparse-Inter-action-Multi-Agent-Systems | Context-Sensitive Reward Shaping for Sparse Inter-action Multi-Agent Systems]]

=== Inspirations Constructivistes ===
   * [[memento-Intrinsically-Motivated-RL | Intrinsically Motivated RL [Singh2005]]]

==== Value function approximation ====
   * [[memento-Value-function-approximation | Quelques infos]]

==== Temporal Difference - Growing Neural Gas ====
   * [[memento-td-gng | TD-GNG]]

===== Réflexions  =====
   * [[reflexion-gng-qc | CQ-Learning et TD-GNG]]

===== Comptes-rendu de réunion  =====

Dossier contenant les tous les slides présentés lors des réunions :
[[https://drive.google.com/drive/folders/0B7dh6En0bP-KakRNYllvOVN3N2c | slides]]

   * [[ reu02-03-17 |02/03/17]]
   * 14/03/17