中間視覚表現によるロバスト方策：マニピュレーションとナビゲーションにおける実験的研究
Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation
深層強化学習に中間視覚表現を組み込むことで、サンプル効率と汎化性能が向上し、ドメインランダム化より大きなドメインシフトにも対応できることをマニピュレーションとナビゲーションで示した。
著者: Bryan Chen, Alexander Sax, Gene Lewis, Iro Armeni, Silvio Savarese, Amir Zamir, Jitendra Malik, Lerrel Pinto
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
Vision-based robotics often separates the control loop into one module for perception and a separate module for control. It is possible to train the whole system end-to-end (e.g. with deep RL), but doing it "from scratch" comes with a high sample complexity cost and the final result is often brittle, failing unexpectedly if the test environment differs from that of training. We study the effects of using mid-level visual representations (features learned asynchronously for traditional computer vision objectives), as a generic and easy-to-decode perceptual state in an end-to-end RL framework. Mid-level representations encode invariances about the world, and we show that they aid generalization, improve sample complexity, and lead to a higher final performance. Compared to other approaches for incorporating invariances, such as domain randomization, asynchronously trained mid-level representations scale better: both to harder problems and to larger domain shifts. In practice, this means that mid-level representations could be used to successfully train policies for tasks where domain randomization and learning-from-scratch failed. We report results on both manipulation and navigation tasks, and for navigation include zero-shot sim-to-real experiments on real robots.
