Heess, N;
Wayne, G;
Tassa, Y;
Lillicrap, T;
Riedmiller, M;
Silver, D;
(2016)
Learning and Transfer of Modulated Locomotor Controllers.
ArXiv: Ithaca, NY, USA.
Preview |
Text
Silver_1610.05182.pdf Download (9MB) | Preview |
Abstract
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 (see attached video).
Type: | Working / discussion paper |
---|---|
Title: | Learning and Transfer of Modulated Locomotor Controllers |
Open access status: | An open access version is available from UCL Discovery |
Publisher version: | https://arxiv.org/abs/1610.05182v1 |
Language: | English |
UCL classification: | UCL UCL > Provost and Vice Provost Offices UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
URI: | https://discovery.ucl.ac.uk/id/eprint/1523405 |
Archive Staff Only
View Item |