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/報酬設計arXiv:2309.06687

自己洗練型大規模言語モデルによるロボティクス深層強化学習のための報酬関数自動設計

Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics

シェア:XThreadsFacebookLINEはてブBluesky

大規模言語モデルが自然言語入力から初期報酬関数を生成し、その性能評価をフィードバックして自己洗練させることで、手設計に匹敵・凌駕する報酬関数を自動設計するフレームワークを提案。

著者: Jiayang Song, Zhehua Zhou, Jiawei Liu, Chunrong Fang, Zhan Shu, Lei Ma

分類: cs.RO, cs.AI

原文アブストラクト

Although Deep Reinforcement Learning (DRL) has achieved notable success in numerous robotic applications, designing a high-performing reward function remains a challenging task that often requires substantial manual input. Recently, Large Language Models (LLMs) have been extensively adopted to address tasks demanding in-depth common-sense knowledge, such as reasoning and planning. Recognizing that reward function design is also inherently linked to such knowledge, LLM offers a promising potential in this context. Motivated by this, we propose in this work a novel LLM framework with a self-refinement mechanism for automated reward function design. The framework commences with the LLM formulating an initial reward function based on natural language inputs. Then, the performance of the reward function is assessed, and the results are presented back to the LLM for guiding its self-refinement process. We examine the performance of our proposed framework through a variety of continuous robotic control tasks across three diverse robotic systems. The results indicate that our LLM-designed reward functions are able to rival or even surpass manually designed reward functions, highlighting the efficacy and applicability of our approach.

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