Learning sequences of compatible actions among agents

Artificial Intelligence Review

Volumn 17, Issue 1, 2002, Pages 21-37

  Polat, Faruk ^a   Abul, Osman ^a  

^a MIDDLE EAST TECHNICAL UNIVERSITY   (Turkey)

Author keywords

Bucket brigade learning; Multiagent learning; Multiagent systems; Q learning; Reinforcement learning

Indexed keywords

CONSTRAINT THEORY; HEURISTIC METHODS; ITERATIVE METHODS; LEARNING ALGORITHMS; LEARNING SYSTEMS;

BUCKET BRIGADE LEARNING; MULTIAGENT LEARNING ALGORITHMS; Q LEARNING; REINFORCEMENT LEARNING;

MULTI AGENT SYSTEMS;

EID: 0036500070     PISSN: 02692821     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1015009422110     Document Type: Article

References (22)

1. Function approximation based multiagent reinforcement learning
2. Multiagent reinforcement learning using function approximation
3. Multiagent reinforcement learning: Theoretical framework and an algorithm
4. Planning and acting in partially observable stochastic domains
5. Learning better in dynamic, partially observable environments
6. Markov games as a framework for multiagent reinforcement learning
7. Introduction to Monte Carlo methods
8. A negotiation platform for cooperating multiagent systems
9. A conflict resolution based decentralized multiagent problem solving model
10. Learning to coordinate without sharing information
11. Multiagent coordination with learning classifier systems
12. Individual learning of coordination knowledge
13. Generalization in reinforcement learning: Successful examples using sparse coarse coding
14. Technical note: Q-learning
15. Learning to coordinate actions in multiagent systems