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:2102.09677

観測干渉に頑健なQネットワークの学習

Training a Resilient Q-Network against Observational Interference

シェア:XThreadsFacebookLINEはてブBluesky

因果推論に基づくDQN(CIQ)を提案し、ノイズや画面停止などの観測干渉を補助タスクとして学習させることで、干渉下でも高い性能と頑健性を実現した。

著者: Chao-Han Huck Yang, I-Te Danny Hung, Yi Ouyang, Pin-Yu Chen

分類: cs.LG, cs.AI, cs.NE, cs.RO, cs.SY, eess.SY

原文アブストラクト

Deep reinforcement learning (DRL) has demonstrated impressive performance in various gaming simulators and real-world applications. In practice, however, a DRL agent may receive faulty observation by abrupt interferences such as black-out, frozen-screen, and adversarial perturbation. How to design a resilient DRL algorithm against these rare but mission-critical and safety-crucial scenarios is an essential yet challenging task. In this paper, we consider a deep q-network (DQN) framework training with an auxiliary task of observational interferences such as artificial noises. Inspired by causal inference for observational interference, we propose a causal inference based DQN algorithm called causal inference Q-network (CIQ). We evaluate the performance of CIQ in several benchmark DQN environments with different types of interferences as auxiliary labels. Our experimental results show that the proposed CIQ method could achieve higher performance and more resilience against observational interferences.

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

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI