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:2407.08464

時間距離を考慮した表現による教師なし目標条件付き強化学習

TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations

シェア:XThreadsFacebookLINEはてブBluesky

時間距離を活用して探索と目標到達を促す教師なし目標条件付き強化学習手法TLDRを提案し、複数の移動環境で広い状態空間の獲得性能を向上させた。

著者: Junik Bae, Kwanyoung Park, Youngwoon Lee

分類: cs.LG, cs.AI

原文アブストラクト

Unsupervised goal-conditioned reinforcement learning (GCRL) is a promising paradigm for developing diverse robotic skills without external supervision. However, existing unsupervised GCRL methods often struggle to cover a wide range of states in complex environments due to their limited exploration and sparse or noisy rewards for GCRL. To overcome these challenges, we propose a novel unsupervised GCRL method that leverages TemporaL Distance-aware Representations (TLDR). Based on temporal distance, TLDR selects faraway goals to initiate exploration and computes intrinsic exploration rewards and goal-reaching rewards. Specifically, our exploration policy seeks states with large temporal distances (i.e. covering a large state space), while the goal-conditioned policy learns to minimize the temporal distance to the goal (i.e. reaching the goal). Our results in six simulated locomotion environments demonstrate that TLDR significantly outperforms prior unsupervised GCRL methods in achieving a wide range of states.

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

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