Markov Decision Processes with Slow Scale Periodic Decisions.
Matthew W. JacobsonNahum ShimkinAdam ShwartzPublished in: Math. Oper. Res. (2003)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- transition matrices
- dynamic programming
- reinforcement learning
- decision processes
- infinite horizon
- state space
- policy iteration
- decision making
- action space
- finite horizon
- average cost
- model based reinforcement learning
- factored mdps
- decision theoretic planning
- partially observable
- reachability analysis
- state and action spaces
- planning under uncertainty
- average reward
- decision makers
- reinforcement learning algorithms
- markov decision process
- decision process
- risk sensitive
- state abstraction
- heuristic search
- learning algorithm