変調された運動制御器の学習と転移
Learning and Transfer of Modulated Locomotor Controllers
脊髄様の低レベルネットワークを単純タスクで事前学習して固定し、高レベル皮質様ネットワークがその入力を変調して複数の運動タスクを学習・転移する手法を提案。
著者: Nicolas Heess, Greg Wayne, Yuval Tassa, Timothy Lillicrap, Martin Riedmiller, David Silver
分類: cs.RO, cs.AI
原文アブストラクト
We study a novel architecture and training procedure for locomotion tasks. A high-frequency, low-level "spinal" network with access to proprioceptive sensors learns sensorimotor primitives by training on simple tasks. This pre-trained module is fixed and connected to a low-frequency, high-level "cortical" network, with access to all sensors, which drives behavior by modulating the inputs to the spinal network. Where a monolithic end-to-end architecture fails completely, learning with a pre-trained spinal module succeeds at multiple high-level tasks, and enables the effective exploration required to learn from sparse rewards. We test our proposed architecture on three simulated bodies: a 16-dimensional swimming snake, a 20-dimensional quadruped, and a 54-dimensional humanoid. Our results are illustrated in the accompanying video at https://youtu.be/sboPYvhpraQ
