Risk-sensitive control of Markov decision processes: A moment-based approach with target distributions.
Rainer SchlosserPublished in: Comput. Oper. Res. (2020)
Keyphrases
- risk sensitive
- markov decision processes
- optimal control
- control policies
- optimal policy
- state space
- reinforcement learning
- finite state
- policy iteration
- utility function
- dynamic programming
- planning under uncertainty
- model free
- finite horizon
- infinite horizon
- partially observable
- control strategies
- reinforcement learning algorithms
- control strategy
- average cost
- markov decision process
- action space
- optimality criterion
- control system
- reward function
- probability distribution
- markov decision problems
- steady state
- control policy
- multistage