模倣・シミュレーション・適応によるロボット学習の効率的な監督
Efficient Supervision for Robot Learning via Imitation, Simulation, and Adaptation
模倣学習・ドメイン適応・シミュレーションからの転移という3つの方向から、ロボット学習のデータパイプラインを効率化する手法を提案した論文。
著者: Markus Wulfmeier
分類: cs.LG, cs.AI, cs.RO, stat.ML
原文アブストラクト
Recent successes in machine learning have led to a shift in the design of autonomous systems, improving performance on existing tasks and rendering new applications possible. Data-focused approaches gain relevance across diverse, intricate applications when developing data collection and curation pipelines becomes more effective than manual behaviour design. The following work aims at increasing the efficiency of this pipeline in two principal ways: by utilising more powerful sources of informative data and by extracting additional information from existing data. In particular, we target three orthogonal fronts: imitation learning, domain adaptation, and transfer from simulation.
