1 citations · 2 across the 8 of their papers we have counts for
11 papers
Improving Online Reinforcement Learning via Bidirectional Behavior Prior Distillation
Gong Gao, Xiao Lai, Jiaji Shen +3
Online reinforcement learning (RL) algorithms frequently exhibit poor sample efficiency and unstable learning dynamics, stemming from systematic critic estimation errors that are e…
Improving Generalization and Robustness in Offline Reinforcement Learning via Boundary-Aware Data Augmentation
Gong Gao, Weidong Zhao, Xianhui Liu
Current offline reinforcement learning (ORL) algorithms tend to overfit the training dataset and exhibit poor in-distribution generalization and robustness performance when deploye…
Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning
Gong Gao, Xiao Lai, Ziqi Xie +3
Deep off-policy reinforcement learning algorithms for continuous control typically rely on neural value function approximation to guide policy improvement. However, temporal-differ…
Expert Behavior Prior Reinforcement Learning
Gong Gao, Weidong Zhao, Xianhui Liu +1
Behavior prior reinforcement learning (BPRL) has emerged as a promising paradigm to improve sample efficiency in online reinforcement learning (RL) by leveraging policy priors deri…
Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action
Gong Gao, Weidong Zhao, Xianhui Liu +1
Existing value-based online reinforcement learning (RL) algorithms suffer from slow policy exploitation due to ineffective exploration and delayed policy updates. To address these…
FAR-AMTN: Attention Multi-Task Network for Face Attribute Recognition
Gong Gao, Zekai Wang, Xianhui Liu +1
To enhance the generalization performance of Multi-Task Networks (MTN) in Face Attribute Recognition (FAR), it is crucial to share relevant information across multiple related pred…
Mask-Guided Multi-Task Network for Face Attribute Recognition
Gong Gao, Zekai Wang, Jian Zhao +3
Face Attribute Recognition (FAR) plays a crucial role in applications such as person re-identification, face retrieval, and face editing. Conventional multi-task attribute recognit…
VisionSafeEnhanced VPC: Cautious Predictive Control with Visibility Constraints under Uncertainty for Autonomous Robotic Surgery
Wang Jiayin, Wei Yanran, Jiang Lei +4
Autonomous control of the laparoscope in robot-assisted Minimally Invasive Surgery (MIS) has received considerable research interest due to its potential to improve surgical safety…
Image-to-Force Estimation for Soft Tissue Interaction in Robotic-Assisted Surgery Using Structured Light
Jiayin Wang, Mingfeng Yao, Yanran Wei +3
For Minimally Invasive Surgical (MIS) robots, accurate haptic interaction force feedback is essential for ensuring the safety of interacting with soft tissue. However, most existin…
Modification Takes Courage: Seamless Image Stitching via Reference-Driven Inpainting
Ziqi Xie, Xiao Lai, Weidong Zhao +3
Current image stitching methods often produce noticeable seams in challenging scenarios such as uneven hue and large parallax. To tackle this problem, we propose the Reference-Driv…
Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model
Ziqi Xie, Weidong Zhao, Xianhui Liu +2
Deep learning-based image stitching pipelines are typically divided into three cascading stages: registration, fusion, and rectangling. Each stage requires its own network training…