日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

オフライン強化学習arXiv:2405.11206

堅牢な方策に向けて:敵対的攻撃と防御によるオフライン強化学習の強化

Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses

シェア:XThreadsFacebookLINEはてブBluesky

オフライン強化学習の方策を敵対的攻撃と防御で強化する枠組みを提案し、D4RLベンチマークで4種の攻撃と2種の防御を評価して堅牢性向上を実証した。

著者: Thanh Nguyen, Tung M. Luu, Tri Ton, Chang D. Yoo

分類: cs.LG, cs.AI, cs.RO

原文アブストラクト

Offline reinforcement learning (RL) addresses the challenge of expensive and high-risk data exploration inherent in RL by pre-training policies on vast amounts of offline data, enabling direct deployment or fine-tuning in real-world environments. However, this training paradigm can compromise policy robustness, leading to degraded performance in practical conditions due to observation perturbations or intentional attacks. While adversarial attacks and defenses have been extensively studied in deep learning, their application in offline RL is limited. This paper proposes a framework to enhance the robustness of offline RL models by leveraging advanced adversarial attacks and defenses. The framework attacks the actor and critic components by perturbing observations during training and using adversarial defenses as regularization to enhance the learned policy. Four attacks and two defenses are introduced and evaluated on the D4RL benchmark. The results show the vulnerability of both the actor and critic to attacks and the effectiveness of the defenses in improving policy robustness. This framework holds promise for enhancing the reliability of offline RL models in practical scenarios.

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