Search Results for author: Baiyu Peng

Found 4 papers, 0 papers with code

Separated Proportional-Integral Lagrangian for Chance Constrained Reinforcement Learning

no code implementations17 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

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

no code implementations19 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.

Mixed Reinforcement Learning with Additive Stochastic Uncertainty

no code implementations28 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.


Cannot find the paper you are looking for? You can Submit a new open access paper.