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:2209.07324

局所最適方策に潜む不安定制御

Example When Local Optimal Policies Contain Unstable Control

シェア:XThreadsFacebookLINEはてブBluesky

強化学習の方策が動的パラメータに対して不安定な制御を含み、それが過学習によりロバスト性と汎化を損なうことを示し、安定性制約と終端制約を提案した。

著者: Bing Song, Jean-Jacques Slotine, Quang-Cuong Pham

分類: cs.RO

原文アブストラクト

We provide a new perspective to understand why reinforcement learning (RL) struggles with robustness and generalization. We show, by examples, that local optimal policies may contain unstable control for some dynamic parameters and overfitting to such instabilities can deteriorate robustness and generalization. Contraction analysis of neural control reveals that there exists boundaries between stable and unstable control with respect to the input gradients of control networks. Ignoring those stability boundaries, learning agents may label the actions that cause instabilities for some dynamic parameters as high value actions if those actions can improve the expected return. The small fraction of such instabilities may not cause attention in the empirical studies, a hidden risk for real-world applications. Those instabilities can manifest themselves via overfitting, leading to failures in robustness and generalization. We propose stability constraints and terminal constraints to solve this issue, demonstrated with a proximal policy optimization example.

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. 2GXO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
  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. 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

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