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/制御arXiv:2409.09869

批評家をリアプノフ関数として用いる安定化強化学習エージェント

Critic as Lyapunov function (CALF): a model-free, stability-ensuring agent

シェア:XThreadsFacebookLINEはてブBluesky

批評家ネットワークをリアプノフ関数として扱い、モデルフリーで各エピソード中に動的システムの安定性を保証する強化学習エージェントCALFを提案し、移動ロボットシミュレータで学習性能の向上を示した。

著者: Pavel Osinenko, Grigory Yaremenko, Roman Zashchitin, Anton Bolychev, Sinan Ibrahim, Dmitrii Dobriborsci

分類: cs.RO, cs.AI, math.OC

原文アブストラクト

This work presents and showcases a novel reinforcement learning agent called Critic As Lyapunov Function (CALF) which is model-free and ensures online environment, in other words, dynamical system stabilization. Online means that in each learning episode, the said environment is stabilized. This, as demonstrated in a case study with a mobile robot simulator, greatly improves the overall learning performance. The base actor-critic scheme of CALF is analogous to SARSA. The latter did not show any success in reaching the target in our studies. However, a modified version thereof, called SARSA-m here, did succeed in some learning scenarios. Still, CALF greatly outperformed the said approach. CALF was also demonstrated to improve a nominal stabilizer provided to it. In summary, the presented agent may be considered a viable approach to fusing classical control with reinforcement learning. Its concurrent approaches are mostly either offline or model-based, like, for instance, those that fuse model-predictive control into the agent.

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