4 papers
Curvature-Aware Zeroth-Order Optimization for Memory-Efficient Test-Time Adaptation
Junming Zhang, Shuyu Yin, Peilin Liu +2
Test-time adaptation (TTA) aims to enhance the cross-domain performance of pre-trained models by adapting to unlabeled test data. While most existing TTA methods rely on backpropag…
Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior
Haochen Niu, Kanyu Zhang, Shuyu Yin +3
In real-world robotic manipulation, states typically admit a neighborhood of near-equivalent actions. That is, for each state, there exist a feasible action neighborhood (FAN) rath…
Analyzing and Bridging the Gap between Maximizing Total Reward and Discounted Reward in Deep Reinforcement Learning
Shuyu Yin, Fei Wen, Peilin Liu +1
The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the idea…
Probing Implicit Bias in Semi-gradient Q-learning: Visualizing the Effective Loss Landscapes via the Fokker--Planck Equation
Shuyu Yin, Fei Wen, Peilin Liu +1
Semi-gradient Q-learning is applied in many fields, but due to the absence of an explicit loss function, studying its dynamics and implicit bias in the parameter space is challengi…