日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

VLAarXiv:2409.15922

豊富な報酬の落とし穴:VLM報酬のノイズを理解し軽減する

The Dark Side of Rich Rewards: Understanding and Mitigating Noise in VLM Rewards

シェア:XThreadsFacebookLINEはてブBluesky

VLMが生成する報酬信号の偽陽性ノイズが強化学習エージェントの性能を低下させることを明らかにし、二値相互情報量(BiMI)報酬関数でノイズを軽減する手法を提案した。

著者: Sukai Huang, Shu-Wei Liu, Nir Lipovetzky, Trevor Cohn

分類: cs.LG, cs.RO

原文アブストラクト

While Vision-Language Models (VLMs) are increasingly used to generate reward signals for training embodied agents to follow instructions, our research reveals that agents guided by VLM rewards often underperform compared to those employing only intrinsic (exploration-driven) rewards, contradicting expectations set by recent work. We hypothesize that false positive rewards -- instances where unintended trajectories are incorrectly rewarded -- are more detrimental than false negatives. Our analysis confirms this hypothesis, revealing that the widely used cosine similarity metric is prone to false positive reward estimates. To address this, we introduce BiMI ({Bi}nary {M}utual {I}nformation), a novel reward function designed to mitigate noise. BiMI significantly enhances learning efficiency across diverse and challenging embodied navigation environments. Our findings offer a nuanced understanding of how different types of reward noise impact agent learning and highlight the importance of addressing multimodal reward signal noise when training embodied agents

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  4. 4GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  5. 5Google DeepMind、ロボット向けAIを発表新製品・発表

PR・アフィリエイト広告

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI