Variability Sensitive Markov Decision Processes.
Melike Baykal-GürsoyKeith W. RossPublished in: Math. Oper. Res. (1992)
Keyphrases
- markov decision processes
- finite state
- state space
- policy iteration
- optimal policy
- dynamic programming
- decision theoretic planning
- reachability analysis
- finite horizon
- transition matrices
- reinforcement learning
- reinforcement learning algorithms
- infinite horizon
- factored mdps
- model based reinforcement learning
- average cost
- action sets
- state and action spaces
- planning under uncertainty
- state abstraction
- discounted reward
- average reward
- decision processes
- multi agent
- action space
- data mining
- partially observable markov decision processes