Asymptotically Optimal Strategies for Adaptive Zero-Sum Discounted Markov Games.
J. Adolfo Minjárez-SosaOscar Vega-AmayaPublished in: SIAM J. Control. Optim. (2009)
Keyphrases
- markov games
- markov decision processes
- optimal strategy
- markov decision process
- decision problems
- optimal policy
- multiagent reinforcement learning
- state space
- reinforcement learning algorithms
- finite state
- reinforcement learning
- monte carlo
- dynamic programming
- finite horizon
- average cost
- control problems
- expected cost
- stochastic games
- mathematical models
- average reward
- policy iteration
- decision making
- infinite horizon
- adaptive control
- np hard
- worst case
- game theoretic
- markov chain
- multi agent systems
- complex systems