日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

強化学習/実機ロボットarXiv:2203.12759

実時間ロボット制御のための非同期強化学習

Asynchronous Reinforcement Learning for Real-Time Control of Physical Robots

シェア:XThreadsFacebookLINEはてブBluesky

ロボットアームの視覚タスクで、学習更新と環境相互作用を非同期化する強化学習システムを実装し、逐次処理との性能を実環境で比較した。学習コストが高い場合、非同期が適切な行動周期を維持し大幅に優れることを示した。

著者: Yufeng Yuan, A. Rupam Mahmood

分類: cs.RO, cs.AI

原文アブストラクト

An oft-ignored challenge of real-world reinforcement learning is that the real world does not pause when agents make learning updates. As standard simulated environments do not address this real-time aspect of learning, most available implementations of RL algorithms process environment interactions and learning updates sequentially. As a consequence, when such implementations are deployed in the real world, they may make decisions based on significantly delayed observations and not act responsively. Asynchronous learning has been proposed to solve this issue, but no systematic comparison between sequential and asynchronous reinforcement learning was conducted using real-world environments. In this work, we set up two vision-based tasks with a robotic arm, implement an asynchronous learning system that extends a previous architecture, and compare sequential and asynchronous reinforcement learning across different action cycle times, sensory data dimensions, and mini-batch sizes. Our experiments show that when the time cost of learning updates increases, the action cycle time in sequential implementation could grow excessively long, while the asynchronous implementation can always maintain an appropriate action cycle time. Consequently, when learning updates are expensive, the performance of sequential learning diminishes and is outperformed by asynchronous learning by a substantial margin. Our system learns in real-time to reach and track visual targets from pixels within two hours of experience and does so directly using real robots, learning completely from scratch.

  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

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI