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:2002.12089

少数の専門家デモで効率的に誘導する深層強化学習

Exploration-efficient Deep Reinforcement Learning with Demonstration Guidance for Robot Control

シェア:XThreadsFacebookLINEはてブBluesky

SACをベースに、少数の専門家デモから識別器とガイダーを学習し、適切な状態でエージェントを誘導することで探索効率と学習安定性を改善した手法を提案。

著者: Ke Lin, Liang Gong, Xudong Li, Te Sun, Binhao Chen, Chengliang Liu, Zhengfeng Zhang, Jian Pu, Junping Zhang

分類: cs.RO

原文アブストラクト

Although deep reinforcement learning (DRL) algorithms have made important achievements in many control tasks, they still suffer from the problems of sample inefficiency and unstable training process, which are usually caused by sparse rewards. Recently, some reinforcement learning from demonstration (RLfD) methods have shown to be promising in overcoming these problems. However, they usually require considerable demonstrations. In order to tackle these challenges, on the basis of the SAC algorithm we propose a sample efficient DRL-EG (DRL with efficient guidance) algorithm, in which a discriminator D(s) and a guider G(s) are modeled by a small number of expert demonstrations. The discriminator will determine the appropriate guidance states and the guider will guide agents to better exploration in the training phase. Empirical evaluation results from several continuous control tasks verify the effectiveness and performance improvements of our method over other RL and RLfD counterparts. Experiments results also show that DRL-EG can help the agent to escape from a local optimum.

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. 2GXO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
  3. 3newmo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
  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