Average Optimality in Nonhomogeneous Infinite Horizon Markov Decision Processes.
Allise O. WachsIrwin E. SchochetmanRobert L. SmithPublished in: Math. Oper. Res. (2011)
Keyphrases
- average cost
- markov decision processes
- infinite horizon
- optimal policy
- finite horizon
- finite state
- stationary policies
- single item
- dynamic programming
- state space
- partially observable
- policy iteration
- long run
- markov decision process
- average reward
- markov decision problems
- reinforcement learning
- optimal control
- initial state
- reinforcement learning algorithms
- action space
- planning under uncertainty
- reward function
- multistage
- dec pomdps
- discounted reward
- total cost
- inventory level
- sufficient conditions
- decision making