Markov Decision Processes: Discrete Stochastic Dynamic Programming (Martin L. Puterman).
A. FeinbergPublished in: SIAM Rev. (1996)
Keyphrases
- markov decision processes
- stochastic dynamic programming
- continuous state
- finite state
- action space
- reinforcement learning
- approximate dynamic programming
- policy iteration
- partially observable markov decision processes
- state space
- dynamic programming
- average cost
- optimal policy
- finite horizon
- influence diagrams
- average reward
- state action
- partially observable
- experimental design
- reinforcement learning algorithms
- stochastic games
- control policies
- infinite horizon
- reward function
- robot navigation
- sensitivity analysis
- state dependent
- model free
- markov decision process
- optimal control
- real valued
- heuristic search
- sufficient conditions
- linear programming
- least squares
- active learning
- search algorithm