FOP: Factorizing Optimal Joint Policy of Maximum-Entropy Multi-Agent Reinforcement Learning.
Tianhao ZhangYueheng LiChen WangGuangming XieZongqing LuPublished in: ICML (2021)
Keyphrases
- maximum entropy
- multi agent reinforcement learning
- minimum cross entropy
- maximum entropy principle
- markov models
- dynamic programming
- conditional random fields
- multi agent
- training data
- iterative scaling
- cooperative
- prior knowledge
- optimal policy
- multi agent learning
- transformation based learning
- markov decision processes
- reinforcement learning