Nonzero-sum Risk-Sensitive Average Stochastic Games: The Case of Unbounded Costs.
Qingda WeiXian ChenPublished in: Dyn. Games Appl. (2021)
Keyphrases
- risk sensitive
- stochastic games
- markov decision processes
- average cost
- optimal control
- infinite horizon
- reinforcement learning algorithms
- reinforcement learning
- average reward
- total cost
- utility function
- optimal policy
- long run
- nash equilibria
- state space
- expected utility
- function approximation
- finite horizon
- optimality criterion