強化学習による一般化力のモデリングでシミュレーションから実機への転移を実現
Modelling Generalized Forces with Reinforcement Learning for Sim-to-Real Transfer
状態依存の一般化力を強化学習で最適化し、解析モデルを改良することで、わずか数分の実機データでsim-to-realの制御方策転移を改善するフレームワークを提案した。Sawyerロボットの非把持マニピュレーションで有効性を示した。
著者: Rae Jeong, Jackie Kay, Francesco Romano, Thomas Lampe, Tom Rothorl, Abbas Abdolmaleki, Tom Erez, Yuval Tassa, Francesco Nori
分類: cs.RO, cs.LG
原文アブストラクト
Learning robotic control policies in the real world gives rise to challenges in data efficiency, safety, and controlling the initial condition of the system. On the other hand, simulations are a useful alternative as they provide an abundant source of data without the restrictions of the real world. Unfortunately, simulations often fail to accurately model complex real-world phenomena. Traditional system identification techniques are limited in expressiveness by the analytical model parameters, and usually are not sufficient to capture such phenomena. In this paper we propose a general framework for improving the analytical model by optimizing state dependent generalized forces. State dependent generalized forces are expressive enough to model constraints in the equations of motion, while maintaining a clear physical meaning and intuition. We use reinforcement learning to efficiently optimize the mapping from states to generalized forces over a discounted infinite horizon. We show that using only minutes of real world data improves the sim-to-real control policy transfer. We demonstrate the feasibility of our approach by validating it on a nonprehensile manipulation task on the Sawyer robot.
