On the Importance of Critical Period in Multi-stage Reinforcement Learning.
Junseok ParkInwoo HwangMin Whoo LeeHyunseok OhMin Su LeeYoungki LeeByoung-Tak ZhangPublished in: CoRR (2022)
Keyphrases
- multistage
- reinforcement learning
- dynamic programming
- optimal policy
- production system
- single stage
- lot sizing
- function approximation
- state space
- stochastic optimization
- stochastic programming
- markov decision processes
- inventory systems
- production line
- planning horizon
- learning algorithm
- average cost
- model free
- scheduling problem
- search algorithm
- optimal solution
- machine learning