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arXiv:1709.07643

OptLayer:実世界の深層強化学習のための実用的な制約付き最適化

OptLayer - Practical Constrained Optimization for Deep Reinforcement Learning in the Real World

シェア:XThreadsFacebookLINEはてブBluesky

ニューラルネットが出力する危険な行動を制約を満たす最近傍の行動に変換する層を導入し、実機ロボットでも安全に強化学習できるようにした研究。

著者: Tu-Hoa Pham, Giovanni De Magistris, Ryuki Tachibana

分類: cs.RO, cs.AI

原文アブストラクト

While deep reinforcement learning techniques have recently produced considerable achievements on many decision-making problems, their use in robotics has largely been limited to simulated worlds or restricted motions, since unconstrained trial-and-error interactions in the real world can have undesirable consequences for the robot or its environment. To overcome such limitations, we propose a novel reinforcement learning architecture, OptLayer, that takes as inputs possibly unsafe actions predicted by a neural network and outputs the closest actions that satisfy chosen constraints. While learning control policies often requires carefully crafted rewards and penalties while exploring the range of possible actions, OptLayer ensures that only safe actions are actually executed and unsafe predictions are penalized during training. We demonstrate the effectiveness of our approach on robot reaching tasks, both simulated and in the real world.

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. 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