Differences

This shows you the differences between two versions of the page.

--- m1r2017 [2025/12/22 05:28]
47.128.115.10 old revision restored (2025/07/15 16:45)
+++ m1r2017 [2026/01/04 03:27] (current)
85.8.117.185 old revision restored (2025/07/28 05:06)
@@ Line 17: / Line 17: @@
       * [[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]]
+=== NN ===
+  * GNG article original de Fritzke [[https://www.cs.swarthmore.edu/~meeden/DevelopmentalRobotics/fritzke95.pdf]]
+  * demo de Fritzke [[http://www.demogng.de]]
+=== Construction de représentations en RL ===
+  * Tile Coding et versions adaptatives {{http://www.cs.utexas.edu/~ai-lab/pubs/whitesontr07.ps|adaptative_tile_coding [Whiteson,2007] }} et {{http://www.aaai.org/ocs/index.php/WS/AAAIW10/paper/viewFile/2068/2422|evolutionary_tile_coding [Lin,2010] }}
+  * Combinaison de growing neural gaz GNG et Q-Learning pour discrétisation adaptative de l'espace d'états: http://liris.cnrs.fr/sasem/lib/exe/fetch.php?media=m1r2017:vieira2013tdgngoriginal.pdf
+  * {{http://nn.cs.utexas.edu/downloads/papers/provost.connsci06.pdf|Self-Organizing Distinctive-State Abstraction (SODA) [Kuipers,2006] }}
 === App Constructiviste ===
@@ Line 29: / Line 39: @@
 ===== Mémentos  =====
+A lire :
+   * https://ai.vub.ac.be/ALA2012/downloads/paper4.pdf
+   * http://ir.library.oregonstate.edu/xmlui/bitstream/handle/1957/39192/HolmesParkerChristopherG2013.pdf;sequence=1
 ==== App Constructiviste ====
    * [[compte-rendu-etat-art-these | Etat de l'art (Thèse S. Mazac)]]
@@ Line 36: / Line 49: @@
    * [[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-Independent-reinforcement-learners-cooperative-Markov-games:-a-survey-regarding-coordination-problems | Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems]]
    * [[memento-Context-Sensitive-Reward-Shaping-for-Sparse-Inter-action-Multi-Agent-Systems | Context-Sensitive Reward Shaping for Sparse Inter-action Multi-Agent Systems]]
@@ Line 48: / Line 61: @@
    * [[memento-td-gng | TD-GNG]]
+===== Réalisations  =====
+   * [[realisation_SOM | SOM]]
+   * [[realisation_GNG | GNG]]
+=== Environnement grille ===
+   * [[realisation_env_grille_qlearning | Environnement Grille (+QLearning)]]
+   * [[realisation_env_grille_qlearning_sma| Environnement Grille SMA ILs (QLearning)]]
+   * [[realisation_env_grille_qlearning_sma_jsl | Environnement Grille SMA JSLs (Qlearning)]]
+=== Environnement Gym ===
+   * [[realisation_env_mountainar_gym_qlearning | MountainCar Gym (Qlearning)]]
+   * [[realisation_env_pendulum_gym_qlearning | Pendulum Gym (Qlearning)]]
 ===== Réflexions  =====
    * [[reflexion-gng-qc | CQ-Learning et TD-GNG]]
@@ Line 53: / Line 81: @@
 ===== Comptes-rendu de réunion  =====
-Dossier contenant les tous les slides présentés lors des réunions :
+Dossier contenant les slides présentés lors des réunions :
-[[https://drive.google.com/drive/folders/0B7dh6En0bP-KakRNYllvOVN3N2c | slides]]
+[[https://drive.google.com/drive/folders/0B7dh6En0bP-KakRNYllvOVN3N2c?usp=sharing | slides]]
    * [[ reu02-03-17 |02/03/17]]
-   * 14/03/17
+   * [[ reu14-03-17 |14/03/17]]
+   * [[ reu24-03-17 |24/03/17]]

DokuWiki

Site Tools

Differences

Page Tools