Showing 2026Show all
3 papers · 1 filter
cs.LG2026
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 disagree on the objective. They…
cs.LG2026
NFTR: From Provable Mode-Averaging to Geodesic Subgoal Selection in Offline Goal-Conditioned RL
Erdemt Bao, Xing Lei, Jun Chen +2
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…
cs.LG2026
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…