Zero-Sum Semi-Markov Games with State-Action-Dependent Discount Factors.
Zhihui YuXianping GuoLi XiaPublished in: CoRR (2021)
Keyphrases
- stochastic games
- semi markov
- state action
- nash equilibria
- game theory
- repeated games
- nash equilibrium
- average reward
- markov decision processes
- conditional random fields
- imperfect information
- multi agent
- infinite horizon
- learning automata
- game theoretic
- learning algorithm
- learning agent
- single agent
- reinforcement learning algorithms
- incomplete information