日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

モデルベースRLarXiv:2110.07985

強化学習におけるオンポリシーモデル誤差補正

On-Policy Model Errors in Reinforcement Learning

シェア:XThreadsFacebookLINEはてブBluesky

実データをオンポリシー予測に用い、学習モデルは行動の一般化にのみ使うことで、モデルベースRLの誤差蓄積を抑えつつデータ効率を向上させる手法を提案。

著者: Lukas P. Fröhlich, Maksym Lefarov, Melanie N. Zeilinger, Felix Berkenkamp

分類: cs.LG, cs.RO, cs.SY, eess.SY

原文アブストラクト

Model-free reinforcement learning algorithms can compute policy gradients given sampled environment transitions, but require large amounts of data. In contrast, model-based methods can use the learned model to generate new data, but model errors and bias can render learning unstable or suboptimal. In this paper, we present a novel method that combines real-world data and a learned model in order to get the best of both worlds. The core idea is to exploit the real-world data for on-policy predictions and use the learned model only to generalize to different actions. Specifically, we use the data as time-dependent on-policy correction terms on top of a learned model, to retain the ability to generate data without accumulating errors over long prediction horizons. We motivate this method theoretically and show that it counteracts an error term for model-based policy improvement. Experiments on MuJoCo- and PyBullet-benchmarks show that our method can drastically improve existing model-based approaches without introducing additional tuning parameters.

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