Lexicographic refinements in possibilistic decision trees and finite-horizon Markov decision processes.
Nahla Ben AmorZeineb El KhalfiHélène FargierRégis SabbadinPublished in: Fuzzy Sets Syst. (2019)
Keyphrases
- finite horizon
- markov decision processes
- decision trees
- optimal policy
- optimal stopping
- infinite horizon
- reinforcement learning
- finite state
- state space
- average cost
- policy iteration
- markov decision process
- transition matrices
- dynamic programming
- partially observable
- expected utility
- machine learning
- action space
- control policies
- decision theoretic planning
- reward function
- decision problems
- sufficient conditions
- multi agent