Minimum Average Value-at-Risk for Finite Horizon Semi-Markov Decision Processes in Continuous Time.
Yonghui HuangXianping GuoPublished in: SIAM J. Optim. (2016)
Keyphrases
- finite horizon
- semi markov decision processes
- markov decision processes
- optimal policy
- average cost
- state space
- average reward
- infinite horizon
- optimal stopping
- inventory control
- optimal control
- finite state
- dynamic programming
- single product
- markov chain
- reinforcement learning
- decision problems
- markov decision process
- yield management
- policy iteration
- multistage
- partially observable
- lot size
- dynamical systems
- decision making
- initial state
- non stationary
- learning algorithm
- state variables
- markov decision problems
- least squares
- hidden markov models
- bayesian networks