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:2501.13883

進化戦略による強化学習でのTransformerの訓練

Utilizing Evolution Strategies to Train Transformers in Reinforcement Learning

シェア:XThreadsFacebookLINEはてブBluesky

進化戦略を用いてDecision Transformerを強化学習で訓練し、MuJoCoやAtariで高性能なエージェントを生成できることを示した。

著者: Matyáš Lorenc, Roman Neruda

分類: cs.LG, cs.NE

原文アブストラクト

We explore the capability of evolution strategies to train an agent with a policy based on a transformer architecture in a reinforcement learning setting. We performed experiments using OpenAI's highly parallelizable evolution strategy to train Decision Transformer in the MuJoCo Humanoid locomotion environment and in the environment of Atari games, testing the ability of this black-box optimization technique to train even such relatively large and complicated models (compared to those previously tested in the literature). The examined evolution strategy proved to be, in general, capable of achieving strong results and managed to produce high-performing agents, showcasing evolution's ability to tackle the training of even such complex models.

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. 2Google DeepMind、ロボット向けAIを発表新製品・発表
  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. 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

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