Overtaking and Almost-Sure Optimality for Infinite Horizon Markov Decision Processes.
Arie LeizarowitzPublished in: Math. Oper. Res. (1996)
Keyphrases
- infinite horizon
- markov decision processes
- average cost
- average reward
- optimal policy
- finite horizon
- state space
- policy iteration
- finite state
- dynamic programming
- single item
- markov decision process
- partially observable
- reinforcement learning
- stationary policies
- reinforcement learning algorithms
- planning under uncertainty
- decision problems
- decision processes
- lost sales
- dec pomdps
- initial state
- action space
- optimal control
- least squares
- search algorithm
- optimal solution
- markov decision problems
- decision making
- learning algorithm