不確実性を考慮したデータ集約による深層模倣学習
Uncertainty-Aware Data Aggregation for Deep Imitation Learning
Monte Carlo Dropoutで制御出力の不確実性を見積もり、自信がない状態だけを選んで専門家のデータを集めることで、自動運転などの模倣学習を効率よく改善する手法を提案した。
著者: Yuchen Cui, David Isele, Scott Niekum, Kikuo Fujimura
分類: cs.LG, cs.RO, stat.ML
原文アブストラクト
Estimating statistical uncertainties allows autonomous agents to communicate their confidence during task execution and is important for applications in safety-critical domains such as autonomous driving. In this work, we present the uncertainty-aware imitation learning (UAIL) algorithm for improving end-to-end control systems via data aggregation. UAIL applies Monte Carlo Dropout to estimate uncertainty in the control output of end-to-end systems, using states where it is uncertain to selectively acquire new training data. In contrast to prior data aggregation algorithms that force human experts to visit sub-optimal states at random, UAIL can anticipate its own mistakes and switch control to the expert in order to prevent visiting a series of sub-optimal states. Our experimental results from simulated driving tasks demonstrate that our proposed uncertainty estimation method can be leveraged to reliably predict infractions. Our analysis shows that UAIL outperforms existing data aggregation algorithms on a series of benchmark tasks.
