1

“Distributional Soft Actor-Critic with Diffusion Policy

We proposed DSAC-D (Distributed Soft Actor Critic with Diffusion Policy) to address the challenges of estimating bias in value functions and obtaining multimodal policy representations.

Tong Liu*, Yinuo Wang*, Xujie Song*, Wenjun Zou, Liangfa Chen, Likun Wang, Bin Shuai, Jingliang Duan, Shengbo Eben Li

LipsNet++: Unifying Filter and Controller into a Policy Network

We unified the filtering and control capabilities into a single policy network in RL, achieving SOTA noise robustness and action smoothness in real-world control tasks.

Xujie Song, Liangfa Chen, Tong Liu, Wenxuan Wang, Yinuo Wang, Shentao Qin, Yinsong Ma, Jingliang Duan, Shengbo Eben Li

LipsNet++: Unifying Filter and Controller into a Policy Network

Enhanced DACER Algorithm with Multimodal Q-value Distribution for Risk-Sensitive Stochastic Vehicle Environments

We proposed DACER++, an online multimodal distributional RL algorithm.

Tong Liu, Xujie Song, Wenxuan Wang, Wenjun Zou, Bin Shuai, Haoyu Gao, Weixian He, Jingliang Duan, Shengbo Eben Li

Diffusion Actor-Critic with Entropy Regulator

We proposed DACER, an online reinforcement learning algorithm that utilizes a diffusion model as the actor network to enhance the representational capacity of the policy.

Yinuo Wang, Likun Wang, Yuxuan Jiang, Wenjun Zou, Tong Liu, Xujie Song, Wenxuan Wang, Liming Xiao, Jiang Wu, Jingliang Duan, Shengbo Eben Li

Diffusion Actor-Critic with Entropy Regulator

LipsNet: A Smooth and Robust Neural Network with Adaptive Lipschitz Constant for High Accuracy Optimal Control

We proposed LipsNet, a smooth and robust neural network with adaptive Lipschitz constant, to deal with the action fluctuation problem in RL (reinforcement learning).

Xujie Song, Jingliang Duan, Wenxuan Wang, Shengbo Eben Li, Chen Chen, Bo Cheng, Bo Zhang, Junqing Wei, Xiaoming Simon Wang

LipsNet: A Smooth and Robust Neural Network with Adaptive Lipschitz Constant for High Accuracy Optimal Control

ODE-based Smoothing Neural Network for Reinforcement Learning Tasks

we proposed a variant of neural ODE, called SmODE, to smooth out control actions in RL. A mapping function is incorporated to estimate the changing speed of system dynamics.

Yinuo Wang, Wenxuan Wang, Xujie Song, Tong Liu, Yuming Yin, Liangfa Chen, Likun Wang, Jingliang Duan, Shengbo Eben Li

ODE-based Smoothing Neural Network for Reinforcement Learning Tasks