DecAP: 減衰アクションプライアを用いたトルクベース脚式ロコモーション方策の模倣学習加速
DecAP: Decaying Action Priors for Accelerated Imitation Learning of Torque-Based Legged Locomotion Policies
位置ベース方策で模倣データを生成し、減衰アクションプライアでトルクベース方策の探索を促す二段階学習法を提案。四足ロボットで外乱に対する頑健性を検証した。
著者: Shivam Sood, Ge Sun, Peizhuo Li, Guillaume Sartoretti
分類: cs.RO
原文アブストラクト
Optimal Control for legged robots has gone through a paradigm shift from position-based to torque-based control, owing to the latter's compliant and robust nature. In parallel to this shift, the community has also turned to Deep Reinforcement Learning (DRL) as a promising approach to directly learn locomotion policies for complex real-life tasks. However, most end-to-end DRL approaches still operate in position space, mainly because learning in torque space is often sample-inefficient and does not consistently converge to natural gaits. To address these challenges, we propose a two-stage framework. In the first stage, we generate our own imitation data by training a position-based policy, eliminating the need for expert knowledge to design optimal controllers. The second stage incorporates decaying action priors, a novel method to enhance the exploration of torque-based policies aided by imitation rewards. We show that our approach consistently outperforms imitation learning alone and is robust to scaling these rewards from 0.1x to 10x. We further validate the benefits of torque control by comparing the robustness of a position-based policy to a position-assisted torque-based policy on a quadruped (Unitree Go1) without any domain randomization in the form of external disturbances during training.
