DAGR: 状態条件付き目標表現と差分認識型目標クロスアテンション
DAGR: State-Conditioned Goal Representations via Difference-Aware Goal Cross-Attention
目標条件付き強化学習において、現在の状態を考慮しない従来の目標表現を、マルチスケールのゲート付きクロスアテンションで状態条件付きに改良する手法DAGRを提案した。ナビゲーションタスクで性能が向上するが、操作やパズルではベースラインと同等以下であり、普遍的な改善ではないことを示した。
著者: Xing Lei, Wenyan Yang, Xuetao Zhang, Donglin Wang
分類: cs.LG, stat.ML
原文アブストラクト
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 cannot mark which part of the goal still needs action. The policy must then recover that cue by inverting both encoders. We propose DAGR. It refines the static embedding of any late-fusion encoder into a state-conditioned one through multi-scale gated cross-attention. A near-identity gated residual preserves the base representation. Difference-aware Goal Cross-Attention then biases the attention scores using a per-token state-goal discrepancy map. On OGBench, DAGR improves navigation. Our ablations trace the gain to the gated residual, not to the difference bias that names the method. On manipulation and puzzle tasks it matches or falls below the base. DAGR is a structured refinement, not a universal improvement.