メタ強化学習による産業用ロボット挿入タスクの実世界適応
Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks
シミュレーション上で多様な挿入タスクをメタ強化学習で学習し、実世界では20回未満の試行で方策を適応させて産業用挿入作業を成功させた研究。
著者: Gerrit Schoettler, Ashvin Nair, Juan Aparicio Ojea, Sergey Levine, Eugen Solowjow
分類: cs.LG, cs.RO
原文アブストラクト
Robotic insertion tasks are characterized by contact and friction mechanics, making them challenging for conventional feedback control methods due to unmodeled physical effects. Reinforcement learning (RL) is a promising approach for learning control policies in such settings. However, RL can be unsafe during exploration and might require a large amount of real-world training data, which is expensive to collect. In this paper, we study how to use meta-reinforcement learning to solve the bulk of the problem in simulation by solving a family of simulated industrial insertion tasks and then adapt policies quickly in the real world. We demonstrate our approach by training an agent to successfully perform challenging real-world insertion tasks using less than 20 trials of real-world experience. Videos and other material are available at https://pearl-insertion.github.io/
