Sample-Efficient Reinforcement Learning of Partially Observable Markov Games.
Qinghua LiuCsaba SzepesváriChi JinPublished in: NeurIPS (2022)
Keyphrases
- partially observable
- reinforcement learning
- markov games
- markov decision processes
- reinforcement learning algorithms
- partial observability
- state space
- partially observable environments
- partially observable domains
- dynamical systems
- markov decision problems
- decision problems
- reward function
- optimal policy
- infinite horizon
- finite state
- multiagent reinforcement learning
- function approximation
- temporal difference
- belief state
- markov decision process
- action space
- model free
- machine learning
- dynamic environments
- computational complexity
- learning algorithm