Mixed Reinforcement Learning with Additive Stochastic Uncertainty

no code implementations • 28 Feb 2020 • Yao Mu, Shengbo Eben Li, Chang Liu, Qi Sun, Bingbing Nie, Bo Cheng, Baiyu Peng

This paper presents a mixed reinforcement learning (mixed RL) algorithm by simultaneously using dual representations of environmental dynamics to search the optimal policy with the purpose of improving both learning accuracy and training speed.

reinforcement-learning Reinforcement Learning (RL)

Model-Based Actor-Critic with Chance Constraint for Stochastic System

no code implementations • 19 Dec 2020 • Baiyu Peng, Yao Mu, Yang Guan, Shengbo Eben Li, Yuming Yin, Jianyu Chen

Safety is essential for reinforcement learning (RL) applied in real-world situations.

Model Predictive Control Reinforcement Learning (RL)

Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning

no code implementations • 17 Feb 2021 • Baiyu Peng, Yao Mu, Jingliang Duan, Yang Guan, Shengbo Eben Li, Jianyu Chen

Taking a control perspective, we first interpret the penalty method and the Lagrangian method as proportional feedback and integral feedback control, respectively.

Autonomous Driving reinforcement-learning +1

Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian

no code implementations • 26 Aug 2021 • Baiyu Peng, Jingliang Duan, Jianyu Chen, Shengbo Eben Li, Genjin Xie, Congsheng Zhang, Yang Guan, Yao Mu, Enxin Sun

Based on this, the penalty method is formulated as a proportional controller, and the Lagrangian method is formulated as an integral controller.

reinforcement-learning Reinforcement Learning (RL) +1