Site Tools


Hotfix release available: 2025-05-14a "Librarian". upgrade now! [56.1] (what's this?)
New release available: 2025-05-14 "Librarian". upgrade now! [56] (what's this?)
Hotfix release available: 2024-02-06b "Kaos". upgrade now! [55.2] (what's this?)
Hotfix release available: 2024-02-06a "Kaos". upgrade now! [55.1] (what's this?)
New release available: 2024-02-06 "Kaos". upgrade now! [55] (what's this?)
Hotfix release available: 2023-04-04b "Jack Jackrum". upgrade now! [54.2] (what's this?)
Hotfix release available: 2023-04-04a "Jack Jackrum". upgrade now! [54.1] (what's this?)
New release available: 2023-04-04 "Jack Jackrum". upgrade now! [54] (what's this?)
Hotfix release available: 2022-07-31b "Igor". upgrade now! [53.1] (what's this?)
Hotfix release available: 2022-07-31a "Igor". upgrade now! [53] (what's this?)
New release available: 2022-07-31 "Igor". upgrade now! [52.2] (what's this?)
New release candidate 2 available: rc2022-06-26 "Igor". upgrade now! [52.1] (what's this?)
New release candidate available: 2022-06-26 "Igor". upgrade now! [52] (what's this?)
Hotfix release available: 2020-07-29a "Hogfather". upgrade now! [51.4] (what's this?)
memento-learning-multi-agent-state-space-representations

Differences

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

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
memento-learning-multi-agent-state-space-representations [2025/07/03 14:24]
216.73.216.192 old revision restored (2025/06/29 03:10)
memento-learning-multi-agent-state-space-representations [2025/07/20 17:33] (current)
216.73.216.84 old revision restored (2025/07/20 04:19)
Line 1: Line 1:
 =====Learning multi-agent state space representations===== =====Learning multi-agent state space representations=====
 +
 +==== Quelques informations ====
 +
 +Markov game -> Système multi-agent avec plusieurs sets d'actions, la proba de transition dépend de s, a et s', récompense unique à chaque agent et une transition.
 +
 +Une variante consiste à donner une récompense commune aux agents.
 +
 +
 +Comment apprendre le bon moment auquel doivent se coordonnés les agents ? Quelques ressources dispo :
 +   * Kok & Vlassis, Utile coordination : Learning indepedenies among cooperative agents.
 +   * Spaan & Melo IDMG
 +
 +Détails sur l'IDMG :
 +   * Interaction Driven Markov Game
 +   * Les agents peuvent connaitre la position des autres par la communication ou en les détectant avec les capteurs
 +   * Plus de détails sur l'article de Spaan & Melo...
 +
 +Learning Coordination States :
 +   * Identification des états dans lequel un agent devrait prendre en compte les autres agents quand il choisi une action et qu'il y a besoin de coordination sur celle-ci avec un autre agent.
 +
 +==== CQ-Learning ====
 +
 +
 +
 +
 +
memento-learning-multi-agent-state-space-representations.1751545441.txt.gz · Last modified: 2025/07/03 14:24 by 216.73.216.192