Multi-agent Inverse Reinforcement Learning for Zero-sum Games.
Xiaomin LinPeter A. BelingRandy CogillPublished in: CoRR (2014)
Keyphrases
- inverse reinforcement learning
- multi agent
- bayesian nonparametric
- preference elicitation
- partially observable environments
- reward function
- multi agent systems
- multiple agents
- cooperative
- reinforcement learning
- imperfect information
- single agent
- temporal difference
- multiagent systems
- coalition formation
- markov decision processes
- utility function
- np hard
- artificial intelligence