日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

オフライン強化学習arXiv:2504.01719

非専門家デモを超えて:オフライン強化学習のための結果駆動型行動制約

Beyond Non-Expert Demonstrations: Outcome-Driven Action Constraint for Offline Reinforcement Learning

シェア:XThreadsFacebookLINEはてブBluesky

非専門家による質の低いデモデータでも安全に学習できるよう、行動の生起確率ではなく結果が安全領域に収まるかで評価する新しい保守的報酬機構ODAFを提案し、MuJoCoや迷路タスクで有効性を示した論文。

著者: Ke Jiang, Wen Jiang, Yao Li, Xiaoyang Tan

分類: cs.LG, cs.RO

原文アブストラクト

We address the challenge of offline reinforcement learning using realistic data, specifically non-expert data collected through sub-optimal behavior policies. Under such circumstance, the learned policy must be safe enough to manage distribution shift while maintaining sufficient flexibility to deal with non-expert (bad) demonstrations from offline data.To tackle this issue, we introduce a novel method called Outcome-Driven Action Flexibility (ODAF), which seeks to reduce reliance on the empirical action distribution of the behavior policy, hence reducing the negative impact of those bad demonstrations.To be specific, a new conservative reward mechanism is developed to deal with distribution shift by evaluating actions according to whether their outcomes meet safety requirements - remaining within the state support area, rather than solely depending on the actions' likelihood based on offline data.Besides theoretical justification, we provide empirical evidence on widely used MuJoCo and various maze benchmarks, demonstrating that our ODAF method, implemented using uncertainty quantification techniques, effectively tolerates unseen transitions for improved "trajectory stitching," while enhancing the agent's ability to learn from realistic non-expert data.

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. 3GXO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
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI