Life is Random, Time is Not: Markov Decision Processes with Window Objectives.
Thomas BrihayeFlorent DelgrangeYoussouf OualhadjMickael RandourPublished in: CoRR (2019)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- dynamic programming
- state space
- policy iteration
- finite horizon
- transition matrices
- infinite horizon
- reachability analysis
- average reward
- factored mdps
- reinforcement learning
- average cost
- action space
- decision theoretic planning
- multiple objectives
- planning under uncertainty
- reinforcement learning algorithms
- model based reinforcement learning
- risk sensitive
- markov decision process
- linear programming
- decision processes
- action sets
- discounted reward
- function approximation