Zero-Sum Two Person Perfect Information Semi-Markov Games: A Reduction.
S. SinhaK. G. BakshiPublished in: CoRR (2022)
Keyphrases
- perfect information
- markov games
- markov decision processes
- multiagent reinforcement learning
- reinforcement learning algorithms
- markov decision process
- control problems
- reinforcement learning
- imperfect information
- stochastic games
- state space
- nash equilibrium
- multi agent
- game tree
- game theoretic
- board game
- multiagent systems
- cooperative
- infinite horizon
- game theory
- optimal policy
- model free
- policy iteration