Continuous-Time Zero-Sum Games for Markov Decision Processes with Discounted Risk-Sensitive Cost Criterion.
Subrata GoluiChandan PalSubhamay SahaPublished in: Dyn. Games Appl. (2022)
Keyphrases
- markov decision processes
- risk sensitive
- average cost
- state space
- optimal control
- optimal policy
- finite state
- infinite horizon
- finite horizon
- policy iteration
- reinforcement learning
- dynamic programming
- stationary policies
- average reward
- reward function
- optimality criterion
- markov chain
- planning under uncertainty
- reinforcement learning algorithms
- long run
- partially observable
- dynamical systems
- planning problems
- total cost
- control policy
- markov decision problems
- multistage
- decision processes
- linear programming
- initial state
- decision making