日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

メタ強化学習arXiv:2210.16530

BIMRL: 脳に着想を得たメタ強化学習

BIMRL: Brain Inspired Meta Reinforcement Learning

シェア:XThreadsFacebookLINEはてブBluesky

脳の記憶機構に着想を得た記憶モジュールと新規の内的報酬を組み合わせ、少ない試行で新しいタスクに適応できるメタ強化学習手法を提案した。

著者: Seyed Roozbeh Razavi Rohani, Saeed Hedayatian, Mahdieh Soleymani Baghshah

分類: cs.LG, cs.AI, cs.RO

原文アブストラクト

Sample efficiency has been a key issue in reinforcement learning (RL). An efficient agent must be able to leverage its prior experiences to quickly adapt to similar, but new tasks and situations. Meta-RL is one attempt at formalizing and addressing this issue. Inspired by recent progress in meta-RL, we introduce BIMRL, a novel multi-layer architecture along with a novel brain-inspired memory module that will help agents quickly adapt to new tasks within a few episodes. We also utilize this memory module to design a novel intrinsic reward that will guide the agent's exploration. Our architecture is inspired by findings in cognitive neuroscience and is compatible with the knowledge on connectivity and functionality of different regions in the brain. We empirically validate the effectiveness of our proposed method by competing with or surpassing the performance of some strong baselines on multiple MiniGrid 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. 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. 3Google DeepMind、ロボット向けAIを発表新製品・発表
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5GXO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

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI