Solving an Infinite-Horizon Discounted Markov Decision Process by DC Programming and DCA.
Vinh Thanh HoLe Thi Hoai AnPublished in: ICCSAMA (2016)
Keyphrases
- infinite horizon
- markov decision process
- dc programming
- finite horizon
- optimal policy
- exact penalty
- markov decision processes
- long run
- convex functions
- dynamic programming
- optimal control
- packing problem
- markov decision problems
- average cost
- policy iteration
- partially observable
- state space
- lead time
- dec pomdps
- inventory models
- reinforcement learning
- stationary policies
- upper bound
- initial state
- constrained minimization
- duality gap
- partially observable markov decision processes
- cutting plane