1

FlipNet: Fourier Lipschitz Smooth Policy Network for Reinforcement Learning
We proposed FlipNet, a policy network incorporating Jacobian regularization and a Fourier filter layer. It can be used in most actor-critic RL algorithms to obtain smoother action in real-world applications.
Xujie Song, Liangfa Chen, Tong Liu, Wenxuan Wang, Yinuo Wang, Shentao Qin, Jingliang Duan, Shengbo Eben Li
Video Project page
FlipNet: Fourier Lipschitz Smooth Policy Network for Reinforcement Learning
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
PDF
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
PDF Code Poster Video
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