New Average Optimality Conditions for Semi-Markov Decision Processes in Borel Spaces.
Qingda WeiXianping GuoPublished in: J. Optim. Theory Appl. (2012)
Keyphrases
- optimality conditions
- semi markov decision processes
- markov decision processes
- nonlinear programming
- karush kuhn tucker
- lower level
- average reward
- average cost
- semi infinite programming
- state space
- optimal policy
- finite state
- reinforcement learning
- learning models
- sample size
- linear programming
- constraint qualification