Multitime scale Markov decision processes.
Hyeong Soo ChangPedram Jaefari FardSteven I. MarcusMark A. ShaymanPublished in: IEEE Trans. Autom. Control. (2003)
Keyphrases
- markov decision processes
- finite state
- state space
- transition matrices
- reinforcement learning
- dynamic programming
- policy iteration
- optimal policy
- decision theoretic planning
- infinite horizon
- model based reinforcement learning
- finite horizon
- planning under uncertainty
- reinforcement learning algorithms
- partially observable
- factored mdps
- decision processes
- average reward
- reachability analysis
- action sets
- semi markov decision processes
- risk sensitive
- action space
- markov decision process
- average cost
- decision makers