QuickLAP: 半自律エージェントのための高速言語-行動選好学習
QuickLAP: Quick Language-Action Preference Learning for Semi-Autonomous Agents
物理的な修正と言語によるフィードバックをベイズ的に統合し、LLMを用いて報酬関数をリアルタイムに学習する手法を提案。半自律運転シミュレータで報酬学習誤差を70%以上削減し、ユーザスタディでも高い理解度と協調性が示された。
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: Jordan Abi Nader, David Lee, Nathaniel Dennler, Andreea Bobu
分類: cs.AI, cs.RO
原文アブストラクト
Robots must learn from both what people do and what they say, but either modality alone is often incomplete: physical corrections are grounded but ambiguous in intent, while language expresses high-level goals but lacks physical grounding. We introduce QuickLAP: Quick Language-Action Preference learning, a Bayesian framework that fuses physical and language feedback to infer reward functions in real time. Our key insight is to treat language as a probabilistic observation over the user's latent preferences, clarifying which reward features matter and how physical corrections should be interpreted. QuickLAP uses Large Language Models (LLMs) to extract reward feature attention masks and preference shifts from free-form utterances, which it integrates with physical feedback in a closed-form update rule. This enables fast, real-time, and robust reward learning that handles ambiguous feedback. In a semi-autonomous driving simulator, QuickLAP reduces reward learning error by over 70% compared to physical-only and heuristic multimodal baselines. A 15-participant user study further validates our approach: participants found QuickLAP significantly more understandable and collaborative, and preferred its learned behavior over baselines. Code is available at https://github.com/MIT-CLEAR-Lab/QuickLAP.
