More Risk-Sensitive Markov Decision Processes.
Nicole BäuerleUlrich RiederPublished in: Math. Oper. Res. (2014)
Keyphrases
- risk sensitive
- markov decision processes
- reinforcement learning
- state space
- optimal policy
- policy iteration
- dynamic programming
- finite state
- average cost
- planning under uncertainty
- reinforcement learning algorithms
- finite horizon
- average reward
- partially observable
- infinite horizon
- action space
- np hard
- reward function
- optimal control
- decision processes
- utility function
- markov decision process
- control policies