状態依存損失関数をメタ学習する逆動力学学習
Learning State-Dependent Losses for Inverse Dynamics Learning
メタ学習により状態に依存した損失関数を学習し、オンライン適応時の逆動力学モデルの更新を高速化する手法を提案。シミュレーションと実機データで標準損失より適応速度が向上することを示した。
著者: Kristen Morse, Neha Das, Yixin Lin, Austin S. Wang, Akshara Rai, Franziska Meier
分類: cs.RO, cs.LG
原文アブストラクト
Being able to quickly adapt to changes in dynamics is paramount in model-based control for object manipulation tasks. In order to influence fast adaptation of the inverse dynamics model's parameters, data efficiency is crucial. Given observed data, a key element to how an optimizer updates model parameters is the loss function. In this work, we propose to apply meta-learning to learn structured, state-dependent loss functions during a meta-training phase. We then replace standard losses with our learned losses during online adaptation tasks. We evaluate our proposed approach on inverse dynamics learning tasks, both in simulation and on real hardware data. In both settings, the structured and state-dependent learned losses improve online adaptation speed, when compared to standard, state-independent loss functions.
