On Reinforcement Learning for Turn-based Zero-sum Markov Games.
Devavrat ShahVarun SomaniQiaomin XieZhi XuPublished in: FODS (2020)
Keyphrases
- markov games
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- multiagent reinforcement learning
- markov decision process
- control problems
- state space
- model free
- function approximation
- multiagent systems
- stochastic games
- dynamic programming
- optimal policy
- multi agent
- temporal difference
- temporal difference learning
- finite horizon
- learning algorithm
- policy iteration
- partially observable
- machine learning
- reward function
- adaptive control
- finite state
- supervised learning
- transfer learning
- learning capabilities
- multi agent systems
- cooperative
- learning automata
- action space
- evaluation function