Computational Complexity of Asynchronous Policy Iteration for Two-Player Zero-Sum Markov Games.
Chenyu XuSihai ZhangZhengdao WangPublished in: ICASSP (2024)
Keyphrases
- markov games
- policy iteration
- markov decision processes
- computational complexity
- markov decision process
- reinforcement learning
- reinforcement learning algorithms
- approximate policy iteration
- optimal policy
- state space
- finite state
- average reward
- dynamic programming
- decision problems
- multiagent reinforcement learning
- temporal difference learning
- finite horizon
- model free
- infinite horizon
- markov decision problems
- temporal difference
- partially observable
- average cost
- machine learning
- initial state
- np hard
- cooperative
- transition probabilities