Hierarchical Markov decision process based on DEVS formalism.
Celine KesslerLaurent CapocchiJean François SantucciBernard P. ZeiglerPublished in: WSC (2017)
Keyphrases
- markov decision process
- state space
- markov decision processes
- reinforcement learning
- optimal policy
- hierarchical reinforcement learning
- finite horizon
- initial state
- temporal difference learning
- policy iteration
- infinite horizon
- transition matrices
- transition probabilities
- partial observability
- planning problems
- linear program
- multistage