3 papers
stat.ML2026
Prediction-powered Inference by Mixture of Experts
Yanwu Gu, Linglong Kong, Dong Xia
The rapidly expanding artificial intelligence (AI) industry has produced diverse yet powerful prediction tools, each with its own network architecture, training strategy, data-proc…
cs.LG2025
Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning
Ke Sun, Yingnan Zhao, Enze Shi +4
The remarkable empirical performance of distributional reinforcement learning (RL) has garnered increasing attention to understanding its theoretical advantages over classical RL.…
cs.LG2024
A Distance-based Anomaly Detection Framework for Deep Reinforcement Learning
Hongming Zhang, Ke Sun, Bo Xu +2
In deep reinforcement learning (RL) systems, abnormal states pose significant risks by potentially triggering unpredictable behaviors and unsafe actions, thus impeding the deployme…