We proposed Ising learning algorithm, the first technique to train multilayer feedforward neural networks on Ising machines (quantum computers). The training time is reduced by 90% compared to CPU/GPU.

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.

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.

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.

We proposed a policy network for RL with low-pass filtering ability, named Smonet, to alleviate the action nonsmoothness issue by learning a low-frequency representation within hidden layers.

We proposed a smooth policy network (LipsNeXt) and a smooth distributed soft actor-critic (DSAC-S) algorithm to achieve coordinated optimization of control precision and action smoothness.

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

This paper constructs the multi-vehicle driving scenario as a non-zero-sum game and proposes a novel game control framework, which consider prediction, decision and control as a whole.