Disturbance Attenuation for Systems Governed by Markov Decision Processes.
Peng ShiEl Kébir BoukasYan ShiRamesh K. AgarwalPublished in: ICONIP (1998)
Keyphrases
- markov decision processes
- state space
- optimal policy
- policy iteration
- dynamic programming
- average cost
- reinforcement learning
- planning under uncertainty
- decentralized control
- infinite horizon
- finite horizon
- decision theoretic planning
- model based reinforcement learning
- transition matrices
- reinforcement learning algorithms
- markov decision process
- reachability analysis
- least squares
- decision processes
- average reward