Approximation of two-person zero-sum continuous-time Markov games with average payoff criterion.
José María LorenzoIsmael Hernández-NoriegaTomás Prieto-RumeauPublished in: Oper. Res. Lett. (2015)
Keyphrases
- markov games
- markov decision processes
- nash equilibrium
- multiagent reinforcement learning
- markov decision process
- reinforcement learning algorithms
- state space
- control problems
- reinforcement learning
- stochastic games
- game theory
- average cost
- optimal control
- repeated games
- multiagent systems
- markov chain
- cooperative
- game theoretic
- multi agent
- dynamical systems
- finite state
- infinite horizon
- dynamic programming
- incomplete information
- search space
- function approximation
- transition probabilities
- solving problems
- reward function
- autonomous agents
- optimal policy
- generative model
- policy iteration
- worst case
- multi agent systems