Estimation of the Change of Agents Behavior Strategy Using State-Action History.
Shihori UchidaShigeyuki ObaShin IshiiPublished in: ICANN (2) (2017)
Keyphrases
- state action
- state transitions
- multi agent
- stochastic games
- multi agent systems
- multiagent systems
- cooperative
- multiple agents
- autonomous agents
- single agent
- evaluation function
- action space
- reinforcement learning
- dynamic environments
- learning capabilities
- resource allocation
- average reward
- decision making
- game theoretic
- action selection
- machine learning