Model-Based Reinforcement Learning for Infinite-Horizon Approximate Optimal Tracking.
Rushikesh KamalapurkarLindsey AndrewsPatrick WaltersWarren E. DixonPublished in: IEEE Trans. Neural Networks Learn. Syst. (2017)
Keyphrases
- infinite horizon
- model based reinforcement learning
- markov decision processes
- optimal control
- finite horizon
- dynamic programming
- stochastic demand
- average cost
- single item
- optimal policy
- fixed cost
- inventory policy
- long run
- holding cost
- reinforcement learning
- markov decision process
- markov decision problems
- state space
- partially observable
- lead time
- policy iteration
- single product
- multistage
- approximate solutions
- expected cost
- decision makers
- control strategy