Sample-Efficient Reinforcement Learning of Partially Observable Markov Games.
Qinghua LiuCsaba SzepesváriChi JinPublished in: CoRR (2022)
Keyphrases
- partially observable
- reinforcement learning
- markov games
- markov decision processes
- reinforcement learning algorithms
- state space
- partially observable environments
- partial observability
- dynamical systems
- markov decision problems
- partially observable domains
- function approximation
- markov decision process
- decision problems
- control problems
- policy iteration
- model free
- dynamic programming
- reward function
- infinite horizon
- transfer learning
- temporal difference
- learning algorithm
- finite state
- action space
- multiagent reinforcement learning
- learning capabilities
- dynamic systems
- optimal policy
- search space
- multi agent
- decision making