Converging Coevolutionary Algorithm for Two-Person Zero-Sum Discounted Markov Games With Perfect Information.
Hyeong Soo ChangPublished in: IEEE Trans. Autom. Control. (2008)
Keyphrases
- markov games
- perfect information
- markov decision processes
- coevolutionary algorithm
- cooperative
- multiagent reinforcement learning
- markov decision process
- reinforcement learning algorithms
- reinforcement learning
- optimal policy
- genetic operators
- intelligent search
- state space
- imperfect information
- dynamic programming
- stochastic games
- infinite horizon
- average reward
- genetic algorithm
- finite horizon
- policy iteration
- control problems
- multi agent
- average cost
- game theory
- game tree
- evolutionary algorithm
- multi agent systems
- machine learning
- model free
- search algorithm
- learning process
- human players
- sufficient conditions
- fitness function
- multiagent systems