Maximum Entropy Heterogeneous-Agent Reinforcement Learning.
Jiarong LiuYifan ZhongSiyi HuHaobo FuQiang FuXiaojun ChangYaodong YangPublished in: ICLR (2024)
Keyphrases
- maximum entropy
- reinforcement learning
- multi agent
- action selection
- learning agent
- markov models
- maximum entropy principle
- multi agent systems
- conditional random fields
- agent receives
- random fields
- maximum entropy model
- multiple agents
- minimum cross entropy
- state space
- iterative scaling
- principle of maximum entropy
- machine learning
- reward function
- learning algorithm
- transfer learning
- markov decision process
- generative model
- information retrieval
- transformation based learning