Coarticulation in Markov Decision Processes.
Khashayar RohanimaneshRobert Platt Jr.Sridhar MahadevanRoderic A. GrupenPublished in: NIPS (2004)
Keyphrases
- markov decision processes
- finite state
- state space
- reinforcement learning
- optimal policy
- policy iteration
- dynamic programming
- decision theoretic planning
- transition matrices
- partially observable
- factored mdps
- reachability analysis
- average cost
- infinite horizon
- action space
- planning under uncertainty
- finite horizon
- model based reinforcement learning
- average reward
- reinforcement learning algorithms
- decision processes
- state and action spaces
- discounted reward
- markov decision process
- semi markov decision processes
- reward function
- interval estimation