Utility based Q-learning to facilitate cooperation in Prisoner's Dilemma games.
Koichi MoriyamaPublished in: Web Intell. Agent Syst. (2009)
Keyphrases
- cooperative
- multi agent
- reinforcement learning
- game theory
- multiagent learning
- function approximation
- computer games
- multi agent systems
- state space
- video games
- knowledge retrieval
- educational games
- nash equilibria
- learning algorithm
- decision models
- game theoretic
- optimal policy
- game playing
- game design
- search algorithm
- temporal difference learning
- information sharing
- learning games