日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

模倣学習arXiv:2405.14199

異種エージェント間の適応的教示:疎な報酬下での驚きのバランス

Adaptive Teaching in Heterogeneous Agents: Balancing Surprise in Sparse Reward Scenarios

シェア:XThreadsFacebookLINEはてブBluesky

教師と生徒の能力差がある状況で、教師が「驚き」を指標に生徒の能力に合わせて実演を適応させ、疎な報酬環境での生徒の学習を改善する枠組みを提案した。

著者: Emma Clark, Kanghyun Ryu, Negar Mehr

分類: cs.RO, cs.LG

原文アブストラクト

Learning from Demonstration (LfD) can be an efficient way to train systems with analogous agents by enabling ``Student'' agents to learn from the demonstrations of the most experienced ``Teacher'' agent, instead of training their policy in parallel. However, when there are discrepancies in agent capabilities, such as divergent actuator power or joint angle constraints, naively replicating demonstrations that are out of bounds for the Student's capability can limit efficient learning. We present a Teacher-Student learning framework specifically tailored to address the challenge of heterogeneity between the Teacher and Student agents. Our framework is based on the concept of ``surprise'', inspired by its application in exploration incentivization in sparse-reward environments. Surprise is repurposed to enable the Teacher to detect and adapt to differences between itself and the Student. By focusing on maximizing its surprise in response to the environment while concurrently minimizing the Student's surprise in response to the demonstrations, the Teacher agent can effectively tailor its demonstrations to the Student's specific capabilities and constraints. We validate our method by demonstrating improvements in the Student's learning in control tasks within sparse-reward environments.

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

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