模倣学習における確率的行動予測
Stochastic Action Prediction for Imitation Learning
専門家のデモに含まれるばらつきを自己回帰生成・GAN・変分予測でモデル化し、タスク成功率が大きく向上することを示した論文。
著者: Sagar Gubbi Venkatesh, Nihesh Rathod, Shishir Kolathaya, Bharadwaj Amrutur
分類: cs.LG, cs.RO
原文アブストラクト
Imitation learning is a data-driven approach to acquiring skills that relies on expert demonstrations to learn a policy that maps observations to actions. When performing demonstrations, experts are not always consistent and might accomplish the same task in slightly different ways. In this paper, we demonstrate inherent stochasticity in demonstrations collected for tasks including line following with a remote-controlled car and manipulation tasks including reaching, pushing, and picking and placing an object. We model stochasticity in the data distribution using autoregressive action generation, generative adversarial nets, and variational prediction and compare the performance of these approaches. We find that accounting for stochasticity in the expert data leads to substantial improvement in the success rate of task completion.
