模倣学習における方策と補助軌道の同時最適化
Imitation Learning via Simultaneous Optimization of Policies and Auxiliary Trajectories
オフラインの軌道デモのみから模倣学習する手法CoDEを提案。最適制御のコロケーションに着想を得た補助軌道ネットワークでBPTTの課題を回避し、少ないデモで行動クローニングより高精度に7自由度マニピュレータの動作を再現した。
著者: Mandy Xie, Anqi Li, Karl Van Wyk, Frank Dellaert, Byron Boots, Nathan Ratliff
分類: cs.RO, cs.LG
原文アブストラクト
Imitation learning (IL) is a frequently used approach for data-efficient policy learning. Many IL methods, such as Dataset Aggregation (DAgger), combat challenges like distributional shift by interacting with oracular experts. Unfortunately, assuming access to oracular experts is often unrealistic in practice; data used in IL frequently comes from offline processes such as lead-through or teleoperation. In this paper, we present a novel imitation learning technique called Collocation for Demonstration Encoding (CoDE) that operates on only a fixed set of trajectory demonstrations. We circumvent challenges with methods like back-propagation-through-time by introducing an auxiliary trajectory network, which takes inspiration from collocation techniques in optimal control. Our method generalizes well and more accurately reproduces the demonstrated behavior with fewer guiding trajectories when compared to standard behavioral cloning methods. We present simulation results on a 7-degree-of-freedom (DoF) robotic manipulator that learns to exhibit lifting, target-reaching, and obstacle avoidance behaviors.
