Switching control in multi-mode Markov decision processes.
Zhiyuan RenBruce H. KroghPublished in: CDC (2001)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- state space
- reinforcement learning
- decentralized control
- policy iteration
- transition matrices
- dynamic programming
- reachability analysis
- reinforcement learning algorithms
- planning under uncertainty
- factored mdps
- infinite horizon
- decision processes
- decision theoretic planning
- control strategy
- optimal control
- average cost
- model based reinforcement learning
- finite horizon
- average reward
- action sets
- partially observable
- semi markov decision processes
- reward function
- control problems
- discounted reward
- real time dynamic programming
- state abstraction
- markov decision process