日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

報酬設計arXiv:2101.01860

意味的報酬操作によるワンショット方策誘導

One-shot Policy Elicitation via Semantic Reward Manipulation

シェア:XThreadsFacebookLINEはてブBluesky

計画述語の組み合わせから得られる意味的説明を用いてエージェントの報酬関数を拡張し、より最適な行動を引き出す逐次最適化アルゴリズムSPEARを提案した論文。

著者: Aaquib Tabrez, Ryan Leonard, Bradley Hayes

分類: cs.RO, cs.AI, cs.MA

原文アブストラクト

Synchronizing expectations and knowledge about the state of the world is an essential capability for effective collaboration. For robots to effectively collaborate with humans and other autonomous agents, it is critical that they be able to generate intelligible explanations to reconcile differences between their understanding of the world and that of their collaborators. In this work we present Single-shot Policy Explanation for Augmenting Rewards (SPEAR), a novel sequential optimization algorithm that uses semantic explanations derived from combinations of planning predicates to augment agents' reward functions, driving their policies to exhibit more optimal behavior. We provide an experimental validation of our algorithm's policy manipulation capabilities in two practically grounded applications and conclude with a performance analysis of SPEAR on domains of increasingly complex state space and predicate counts. We demonstrate that our method makes substantial improvements over the state-of-the-art in terms of runtime and addressable problem size, enabling an agent to leverage its own expertise to communicate actionable information to improve another's performance.

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