Learning sequences of actions in collectives of autonomous agents.
Kagan TumerAdrian K. AgoginoDavid H. WolpertPublished in: AAMAS (2002)
Keyphrases
- autonomous agents
- intelligent behavior
- learning process
- multi agent environments
- agent behavior
- learning agents
- reinforcement learning
- agent negotiation
- goal directed
- incomplete information
- multiagent systems
- dynamic environments
- multi agent
- learning algorithm
- mental states
- decision theoretic
- changing environment
- action sequences