日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

ベイズ最適化arXiv:2011.09445

慎重なベイズ最適化による効率的でスケーラブルな方策探索

Cautious Bayesian Optimization for Efficient and Scalable Policy Search

シェア:XThreadsFacebookLINEはてブBluesky

ベイズ最適化の方策探索空間を予測不確実性の劣位集合に制限することで、高次元空間でもスケールし、システム破損リスクを抑える手法を提案し、モータースキルやsim2real課題で有効性を示した。

著者: Lukas P. Fröhlich, Melanie N. Zeilinger, Edgar D. Klenske

分類: cs.RO

原文アブストラクト

Sample efficiency is one of the key factors when applying policy search to real-world problems. In recent years, Bayesian Optimization (BO) has become prominent in the field of robotics due to its sample efficiency and little prior knowledge needed. However, one drawback of BO is its poor performance on high-dimensional search spaces as it focuses on global search. In the policy search setting, local optimization is typically sufficient as initial policies are often available, e.g., via meta-learning, kinesthetic demonstrations or sim-to-real approaches. In this paper, we propose to constrain the policy search space to a sublevel-set of the Bayesian surrogate model's predictive uncertainty. This simple yet effective way of constraining the policy update enables BO to scale to high-dimensional spaces (>100) as well as reduces the risk of damaging the system. We demonstrate the effectiveness of our approach on a wide range of problems, including a motor skills task, adapting deep RL agents to new reward signals and a sim-to-real task for an inverted pendulum system.

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