日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

歩行arXiv:1710.02896

不整地二足歩行のための再帰決定論的方策勾配法

Recurrent Deterministic Policy Gradient Method for Bipedal Locomotion on Rough Terrain Challenge

シェア:XThreadsFacebookLINEはてブBluesky

部分観測環境での二足歩行を解くため、再帰決定論的方策勾配法(RDPG)を改良し、OpenAI GymのBipedal-Walker課題で不整地を長距離歩行できる適応的なエージェントを実現した。

著者: Doo Re Song, Chuanyu Yang, Christopher McGreavy, Zhibin Li

分類: cs.AI, cs.LG, cs.RO

原文アブストラクト

This paper presents a deep learning framework that is capable of solving partially observable locomotion tasks based on our novel interpretation of Recurrent Deterministic Policy Gradient (RDPG). We study on bias of sampled error measure and its variance induced by the partial observability of environment and subtrajectory sampling, respectively. Three major improvements are introduced in our RDPG based learning framework: tail-step bootstrap of interpolated temporal difference, initialisation of hidden state using past trajectory scanning, and injection of external experiences learned by other agents. The proposed learning framework was implemented to solve the Bipedal-Walker challenge in OpenAI's gym simulation environment where only partial state information is available. Our simulation study shows that the autonomous behaviors generated by the RDPG agent are highly adaptive to a variety of obstacles and enables the agent to effectively traverse rugged terrains for long distance with higher success rate than leading contenders.

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

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI