Non-randomized control of constrained Markov decision processes.
Richard C. ChenEugene A. FeinbergPublished in: ACC (2006)
Keyphrases
- markov decision processes
- state space
- optimal policy
- finite state
- transition matrices
- decentralized control
- reinforcement learning
- control system
- average cost
- policy iteration
- reinforcement learning algorithms
- dynamic programming
- partially observable
- action space
- factored mdps
- planning under uncertainty
- control strategy
- finite horizon
- reachability analysis
- decision theoretic planning
- model based reinforcement learning
- markov decision process
- control policy
- average reward
- real time dynamic programming
- data mining
- reward function
- continuous state spaces
- risk sensitive
- action sets
- control policies
- semi markov decision processes
- control problems
- learning algorithm