Multiagent Reinforcement Learning Algorithm Using Temporal Difference Error.
SeungGwan LeePublished in: ISNN (1) (2005)
Keyphrases
- temporal difference
- reinforcement learning
- multi agent
- td learning
- evaluation function
- function approximation
- monte carlo
- model free
- temporal difference learning
- reinforcement learning algorithms
- step size
- policy evaluation
- action selection
- multiagent systems
- supervised learning
- multiple agents
- active learning
- feature selection
- state space
- predictive state representations