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:2012.11538

報酬なしでエージェントを評価する

Evaluating Agents without Rewards

シェア:XThreadsFacebookLINEはてブBluesky

強化学習エージェントの内部目的関数(入力エントロピー・情報利得・エンパワーメント)を既存データ上で事後評価し、タスク報酬よりも人間行動類似度と強く相関することを示した研究。

著者: Brendon Matusch, Jimmy Ba, Danijar Hafner

分類: cs.LG, cs.AI, cs.RO

原文アブストラクト

Reinforcement learning has enabled agents to solve challenging tasks in unknown environments. However, manually crafting reward functions can be time consuming, expensive, and error prone to human error. Competing objectives have been proposed for agents to learn without external supervision, but it has been unclear how well they reflect task rewards or human behavior. To accelerate the development of intrinsic objectives, we retrospectively compute potential objectives on pre-collected datasets of agent behavior, rather than optimizing them online, and compare them by analyzing their correlations. We study input entropy, information gain, and empowerment across seven agents, three Atari games, and the 3D game Minecraft. We find that all three intrinsic objectives correlate more strongly with a human behavior similarity metric than with task reward. Moreover, input entropy and information gain correlate more strongly with human similarity than task reward does, suggesting the use of intrinsic objectives for designing agents that behave similarly to human players.

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

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