一歩ずつ報酬を与えよう:連続環境における視覚言語ナビゲーションのためのステップ認識型対照アライメント
Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments
連続環境での視覚言語ナビゲーションにおいて、失敗軌跡から有効な接頭辞と逸脱点を特定するステップ単位の監査と、状況に応じたグループ構築により、密な報酬信号を抽出して学習を安定化させるSACAを提案し、最先端性能を達成した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Haoyuan Li, Rui Liu, Hehe Fan, Yi Yang
分類: cs.RO, cs.CV
原文アブストラクト
Vision-Language Navigation in Continuous Environments (VLN-CE) requires agents to learn complex reasoning from long-horizon human interactions. While Multi-modal Large Language Models (MLLMs) have driven recent progress, current training paradigms struggle to balance generalization capability, error recovery and training stability. Specifically, (i) policies derived from SFT suffer from compounding errors, struggling to recover from out-of-distribution states, and (ii) Reinforcement Fine-Tuning (RFT) methods e.g. GRPO are bottlenecked by sparse outcome rewards. Their binary feedback fails to assign credit to individual steps, leading to gradient signal collapse in failure dominant batches. To address these challenges, we introduce Step-Aware Contrastive Alignment (SACA), a framework designed to extract dense supervision from imperfect trajectories. At its core, the Perception-Grounded Step-Aware auditor evaluates progress step-by-step, disentangling failed trajectories into valid prefixes and exact divergence points. Leveraging these signals, Scenario-Conditioned Group Construction mechanism dynamically routes batches to specialized resampling and optimization strategies. Extensive experiments on VLN-CE benchmarks demonstrate that SACA achieves state-of-the-art performance.
