Lexicographic refinements in stationary possibilistic Markov Decision Processes.
Nahla Ben AmorZeineb El KhalfiHélène FargierRégis SabbadinPublished in: Int. J. Approx. Reason. (2018)
Keyphrases
- markov decision processes
- stationary policies
- non stationary
- state space
- optimal policy
- reinforcement learning
- finite state
- transition matrices
- policy iteration
- dynamic programming
- planning under uncertainty
- possibility theory
- finite horizon
- model based reinforcement learning
- action sets
- reachability analysis
- average reward
- decision theoretic planning
- factored mdps
- markov decision process
- reinforcement learning algorithms
- infinite horizon
- machine learning
- semi markov decision processes
- decision processes
- action space
- partially observable
- risk sensitive
- data mining
- interval estimation