Iterated risk measures for risk-sensitive Markov decision processes with discounted cost
Takayuki OsogamiPublished in: CoRR (2012)
Keyphrases
- markov decision processes
- risk sensitive
- risk measures
- average cost
- state space
- optimal policy
- finite state
- dynamic programming
- finite horizon
- infinite horizon
- reinforcement learning
- policy iteration
- risk averse
- reinforcement learning algorithms
- partially observable
- decision processes
- markov decision problems
- planning under uncertainty
- multistage
- total cost
- action space
- utility function
- initial state
- decision makers
- average reward
- long run
- markov chain
- control policy
- robust optimization
- optimal control