Utility Based Q-learning to Maintain Cooperation in Prisoner's Dilemma Games.
Koichi MoriyamaPublished in: IAT (2007)
Keyphrases
- cooperative
- multi agent
- game theory
- multiagent learning
- function approximation
- reinforcement learning
- game playing
- video games
- state space
- learning algorithm
- computer games
- temporal difference learning
- game theoretic
- machine learning
- nash equilibrium
- learning rate
- nash equilibria
- learning games
- evolutionary game theory
- multi agent systems
- game design
- stochastic games
- human computation
- online game
- game play
- game development
- imperfect information
- serious games
- information sharing
- optimal policy
- multi agent reinforcement learning