日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

模倣学習arXiv:2301.01348

DADAgger: 不一致拡張データセット集約

DADAgger: Disagreement-Augmented Dataset Aggregation

シェア:XThreadsFacebookLINEはてブBluesky

模倣学習のDAggerを改良し、アンサンブルの予測分散で分布外状態のみを専門家に問い合わせることで、専門家クエリを削減しつつ同等の性能を達成する手法を提案。

著者: Akash Haridas, Karim Hamadeh, Samarendra Chandan Bindu Dash

分類: cs.LG, cs.AI, cs.RO

原文アブストラクト

DAgger is an imitation algorithm that aggregates its original datasets by querying the expert on all samples encountered during training. In order to reduce the number of samples queried, we propose a modification to DAgger, known as DADAgger, which only queries the expert for state-action pairs that are out of distribution (OOD). OOD states are identified by measuring the variance of the action predictions of an ensemble of models on each state, which we simulate using dropout. Testing on the Car Racing and Half Cheetah environments achieves comparable performance to DAgger but with reduced expert queries, and better performance than a random sampling baseline. We also show that our algorithm may be used to build efficient, well-balanced training datasets by running with no initial data and only querying the expert to resolve uncertainty.

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. 3Google DeepMind、ロボット向けAIを発表新製品・発表
  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

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