7 papers · 1 filter
DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention
Xing Lei, Wenyan Yang, Xuetao Zhang +1
Goal-conditioned reinforcement learning hinges on how the goal is encoded. Contrastive, metric, temporal-distance, and information-theoretic encoders differ in objective. They stil…
NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL
Erdemt Bao, Xing Lei, Jun Chen
Hierarchical Implicit Q-Learning (HIQL), an offline goal-conditioned RL method, selects subgoals by value-function advantages alone. This rule has two coupled failure modes. Optimi…
QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL
Xing Lei, Jincheng Wang, Xuetao Zhang +1
Offline goal-conditioned RL (GCRL) learns goal-reaching policies from static datasets, but real-world datasets are often partially observable and history-dependent, exhibiting a mi…
GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning
Xing Lei, Wenyan Yang, Kaiqiang Ke +4
Goal-conditioned reinforcement learning (GCRL) with sparse rewards remains a fundamental challenge in reinforcement learning. While hindsight experience replay (HER) has shown prom…
Closing the Gap between TD Learning and Supervised Learning with -Conditioned Maximization
Xing Lei, Zifeng Zhuang, Shentao Yang +6
Recently, supervised learning (SL) methodology has emerged as an effective approach for offline reinforcement learning (RL) due to their simplicity, stability, and efficiency. Howe…
MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning
Xing Lei, Xuetao Zhang, Donglin Wang
Recently, a state-of-the-art family of algorithms, known as Goal-Conditioned Weighted Supervised Learning (GCWSL) methods, has been introduced to tackle challenges in offline goal-…