actor-critic 1continuous control 1distributional critic 1off-policy rl 1overestimation bias 1uncertainty weighting 1
From the 1 of 3 linked papers with an AI index.
3 papers
cs.LG2026
Collaborative Weighting with Pessimistic Critic for Mitigating Overestimation in Off-Policy Reinforcement Learning
Gong Gao, Xiao Lai, Ziqi Xie +3
The paper introduces Collaborative Weighting Actor-Critic (CWAC), a framework that uses a distributional critic and uncertainty‑aware weighting to reduce overestimation bias in off…
cs.CV2026
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…
cs.CV2025
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…