Stochastic Dominance-Constrained Markov Decision Processes.
William B. HaskellRahul JainPublished in: SIAM J. Control. Optim. (2013)
Keyphrases
- markov decision processes
- stochastic dominance
- fuzzy random variables
- risk sensitive
- state space
- random variables
- finite state
- policy iteration
- optimal policy
- dynamic programming
- transition matrices
- decision theoretic planning
- average cost
- reinforcement learning
- finite horizon
- planning under uncertainty
- partially observable
- average reward
- reinforcement learning algorithms
- reachability analysis
- infinite horizon
- action space
- markov decision process
- decision processes
- probability distribution
- multistage
- state abstraction
- action sets
- model based reinforcement learning
- reward function