Risk-Sensitive Markov Decision Processes with Combined Metrics of Mean and Variance.
Li XiaPublished in: CoRR (2020)
Keyphrases
- risk sensitive
- markov decision processes
- state space
- finite state
- reinforcement learning
- dynamic programming
- optimal policy
- optimal control
- average cost
- policy iteration
- finite horizon
- utility function
- reinforcement learning algorithms
- partially observable
- planning under uncertainty
- infinite horizon
- action space
- average reward
- model free
- markov decision process
- decision processes
- optimality criterion
- markov decision problems