実世界経験でシミュレーションのランダム化を適応させ、sim-to-realのループを閉じる
Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience
実世界での少数の試行を方策学習に交互に組み込み、シミュレーションのパラメータ分布を自動調整することで、実機への方策転移を改善する手法を提案した。
著者: Yevgen Chebotar, Ankur Handa, Viktor Makoviychuk, Miles Macklin, Jan Issac, Nathan Ratliff, Dieter Fox
分類: cs.RO, cs.LG
原文アブストラクト
We consider the problem of transferring policies to the real world by training on a distribution of simulated scenarios. Rather than manually tuning the randomization of simulations, we adapt the simulation parameter distribution using a few real world roll-outs interleaved with policy training. In doing so, we are able to change the distribution of simulations to improve the policy transfer by matching the policy behavior in simulation and the real world. We show that policies trained with our method are able to reliably transfer to different robots in two real world tasks: swing-peg-in-hole and opening a cabinet drawer. The video of our experiments can be found at https://sites.google.com/view/simopt
