Technical Note - Markov Decision Processes with State-Information Lag.
D. M. BrooksCornelius T. LeondesPublished in: Oper. Res. (1972)
Keyphrases
- state information
- markov decision processes
- action space
- state space
- optimal policy
- reinforcement learning
- dynamic programming
- finite state
- transition matrices
- partially observable
- policy iteration
- infinite horizon
- average reward
- average cost
- decision theoretic planning
- state variables
- markov chain
- heuristic search
- markov decision process
- action models
- active learning
- random variables
- objective function