Baselines for Joint-Action Reinforcement Learning of Coordination in Cooperative Multi-agent Systems.
Martin CarpenterDaniel KudenkoPublished in: Adaptive Agents and Multi-Agent Systems (2005)
Keyphrases
- cooperative multi agent systems
- reinforcement learning
- joint action
- multi agent reinforcement learning
- multiagent reinforcement learning
- multi agent
- multi agent systems
- stochastic games
- reinforcement learning algorithms
- markov decision process
- function approximation
- model free
- state space
- dynamic programming
- cooperative
- markov decision processes
- learning capabilities
- partially observable
- temporal difference
- learning agents
- machine learning
- nash equilibria
- learning automata
- action selection
- transfer learning
- optimal policy