Equilibrium play in matches: Binary Markov games.
Mark WalkerJohn WoodersRabah AmirPublished in: Games Econ. Behav. (2011)
Keyphrases
- markov games
- markov decision processes
- multiagent reinforcement learning
- reinforcement learning algorithms
- markov decision process
- reinforcement learning
- control problems
- nash equilibrium
- multiagent systems
- state space
- stochastic games
- cooperative
- multi agent
- dynamic programming
- optimal policy
- policy iteration
- finite horizon
- temporal difference
- game theory
- model free
- optimal stopping
- imperfect information
- dynamic environments
- game playing
- nash equilibria
- game theoretic
- average reward
- markov decision problems
- mobile robot
- infinite horizon