Finite Horizon Reinforcement Learning in Solving Optimal Control of State-Dependent Switched Systems.
Mi ZhouPublished in: CoRR (2023)
Keyphrases
- optimal control
- optimal policy
- infinite horizon
- finite horizon
- state dependent
- reinforcement learning
- dynamic programming
- base stock policy
- markov decision processes
- average cost
- state space
- single product
- partially observable
- markov decision process
- control policies
- control strategy
- long run
- inventory control
- markov decision problems
- single item
- stochastic demand
- brownian motion
- inventory level
- steady state
- multistage
- inventory models
- periodic review
- finite state
- linear programming
- lost sales
- queueing networks
- non stationary
- inventory policy
- queue length
- machine learning