arXiv stat.ML
· Papers
DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention
arXiv:2607.13731v1 Announce Type: cross Abstract: Goal-conditioned reinforcement learning hinges on how the goal is encoded. Contrastive, metric, temporal-distance, and information-theoretic encoders differ in objective. They still share one trait. None of them sees the current state. Such a state-independent embedding