Optimizing Quantiles in Preference-based Markov Decision Processes.
Hugo GilbertPaul WengYan XuPublished in: CoRR (2016)
Keyphrases
- markov decision processes
- optimal policy
- state space
- finite state
- dynamic programming
- reinforcement learning
- policy iteration
- transition matrices
- finite horizon
- planning under uncertainty
- reinforcement learning algorithms
- reachability analysis
- decision theoretic planning
- partially observable
- model based reinforcement learning
- sliding window
- decision processes
- average cost
- infinite horizon
- state and action spaces
- risk sensitive
- semi markov decision processes
- action sets
- average reward
- data mining
- markov decision process
- real time dynamic programming
- interval estimation
- least squares