Zero-sum risk-sensitive continuous-time stochastic games with unbounded payoff and transition rates and Borel spaces.
Junyu ZhangXianping GuoLi XiaPublished in: CoRR (2021)
Keyphrases
- stochastic games
- risk sensitive
- markov decision processes
- repeated games
- state space
- average reward
- optimal control
- optimal policy
- dynamic programming
- reinforcement learning algorithms
- state transition
- reinforcement learning
- finite state
- markov chain
- infinite horizon
- policy iteration
- partially observable
- game theory
- dynamical systems
- average cost
- nash equilibrium
- markov decision process
- finite horizon
- probability distribution
- nash equilibria
- action space