Life is Random, Time is Not: Markov Decision Processes with Window Objectives.
Thomas BrihayeFlorent DelgrangeYoussouf OualhadjMickael RandourPublished in: Log. Methods Comput. Sci. (2020)
Keyphrases
- markov decision processes
- state space
- finite state
- optimal policy
- dynamic programming
- reinforcement learning
- transition matrices
- factored mdps
- reinforcement learning algorithms
- planning under uncertainty
- reachability analysis
- decision theoretic planning
- average reward
- policy iteration
- model based reinforcement learning
- partially observable
- infinite horizon
- markov decision process
- average cost
- state and action spaces
- action space
- risk sensitive
- decision processes
- state abstraction
- semi markov decision processes
- real time dynamic programming
- machine learning
- reward function
- action sets
- linear programming
- data streams