Taming denumerable Markov decision processes with decisiveness.
Nathalie BertrandPatricia BouyerThomas BrihayePaulin FournierPublished in: CoRR (2020)
Keyphrases
- markov decision processes
- finite state
- state space
- optimal policy
- policy iteration
- reinforcement learning
- transition matrices
- dynamic programming
- reachability analysis
- reinforcement learning algorithms
- partially observable
- planning under uncertainty
- infinite horizon
- markov decision process
- finite horizon
- decision theoretic planning
- average cost
- action space
- risk sensitive
- state and action spaces
- linear programming
- action sets
- decision processes
- state abstraction
- heuristic search
- machine learning