Markov decision processes with iterated coherent risk measures.
Shanyun ChuYi ZhangPublished in: Int. J. Control (2014)
Keyphrases
- markov decision processes
- risk measures
- reinforcement learning
- optimal policy
- finite state
- state space
- policy iteration
- transition matrices
- risk averse
- dynamic programming
- markov decision process
- robust optimization
- infinite horizon
- decision theoretic planning
- action sets
- average cost
- bayesian networks
- initial state
- sufficient conditions