Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian.
Baiyu PengJingliang DuanJianyu ChenShengbo Eben LiGenjin XieCongsheng ZhangYang GuanYao MuEnxin SunPublished in: CoRR (2021)
Keyphrases
- chance constrained
- reinforcement learning
- stochastic programming
- robust optimization
- computationally tractable
- chance constraints
- knapsack problem
- chance constrained programming
- reverse logistics
- multistage
- optimal control
- neural network
- third party
- optimal solution
- learning algorithm
- machine learning
- linear program
- state space
- dynamic programming
- inventory control
- evolutionary algorithm