Technical Note - Identifying Forecast Horizons in Nonhomogeneous Markov Decision Processes.
Wallace J. HoppPublished in: Oper. Res. (1989)
Keyphrases
- markov decision processes
- infinite horizon
- finite state
- optimal policy
- reinforcement learning
- state space
- transition matrices
- policy iteration
- reinforcement learning algorithms
- dynamic programming
- finite horizon
- average cost
- model based reinforcement learning
- reachability analysis
- decision theoretic planning
- risk sensitive
- markov decision process
- action space
- lost sales
- planning under uncertainty
- partially observable
- factored mdps
- state abstraction
- decision processes
- machine learning
- multistage
- semi markov decision processes
- state and action spaces
- action sets
- long run
- search algorithm
- stochastic shortest path