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×計画arXiv:2004.11456

自動計画で強化学習のロボット探索を誘導

Guiding Robot Exploration in Reinforcement Learning via Automated Planning

シェア:XThreadsFacebookLINEはてブBluesky

行動知識を用いた自動計画で強化学習エージェントの探索を効率化するGuided Dyna-Qを提案し、移動ロボットのナビゲーションで有効性を示した。

著者: Yohei Hayamizu, Saeid Amiri, Kishan Chandan, Keiki Takadama, Shiqi Zhang

分類: cs.RO, cs.LG

原文アブストラクト

Reinforcement learning (RL) enables an agent to learn from trial-and-error experiences toward achieving long-term goals; automated planning aims to compute plans for accomplishing tasks using action knowledge. Despite their shared goal of completing complex tasks, the development of RL and automated planning has been largely isolated due to their different computational modalities. Focusing on improving RL agents' learning efficiency, we develop Guided Dyna-Q (GDQ) to enable RL agents to reason with action knowledge to avoid exploring less-relevant states. The action knowledge is used for generating artificial experiences from an optimistic simulation. GDQ has been evaluated in simulation and using a mobile robot conducting navigation tasks in a multi-room office environment. Compared with competitive baselines, GDQ significantly reduces the effort in exploration while improving the quality of learned policies.

  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

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