Reinforcement Learning with an Extended Classifier System in Zero-sum Markov Games.
Chang WangHao ChenChao YanXiaojia XiangPublished in: ICA (2019)
Keyphrases
- markov games
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- multiagent reinforcement learning
- markov decision process
- control problems
- state space
- optimal policy
- model free
- stochastic games
- function approximation
- multi agent
- temporal difference learning
- learning algorithm
- temporal difference
- multiagent systems
- machine learning
- infinite horizon
- cooperative
- dynamic programming
- policy iteration
- optimal control
- finite state
- average cost
- action space
- reward function
- resource allocation
- partially observable
- learning automata
- evaluation function
- learning agent
- worst case