CoMic: Complementary Task Learning & Mimicry for Reusable Skills
Leonard Hasenclever, Fabio Pardo, Raia Hadsell, Nicolas Heess, Josh Merel
Abstract
Learning to control complex bodies and reuse learned behaviors is a longstanding challenge in continuous control. We study the problem of learning reusable humanoid skills by imitating motion capture data and joint training with complementary tasks. We show that it is possible to learn reusable skills through reinforcement learning on 50 times more motion capture data than prior work. We systematically compare a variety of different network architectures across different data regimes both in terms of imitation performance as well as transfer to challenging locomotion tasks. Finally we show that it is possible to interleave the motion capture tracking with training on complementary tasks, enriching the resulting skill space, and enabling the reuse of skills not well covered by the motion capture data such as getting up from the ground or catching a ball.
BibTeX
@InProceedings{pmlr-v119-hasenclever20a,
title = {{C}o{M}ic: Complementary Task Learning & Mimicry for Reusable Skills},
author = {Hasenclever, Leonard and Pardo, Fabio and Hadsell, Raia and Heess, Nicolas and Merel, Josh},
booktitle = {Proceedings of the 37th International Conference on Machine Learning},
pages = {4105--4115},
year = {2020},
editor = {III, Hal Daumé and Singh, Aarti},
volume = {119},
series = {Proceedings of Machine Learning Research},
month = {13--18 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v119/hasenclever20a/hasenclever20a.pdf},
url = {https://proceedings.mlr.press/v119/hasenclever20a.html},
abstract = {Learning to control complex bodies and reuse learned behaviors is a longstanding challenge in continuous control. We study the problem of learning reusable humanoid skills by imitating motion capture data and joint training with complementary tasks. We show that it is possible to learn reusable skills through reinforcement learning on 50 times more motion capture data than prior work. We systematically compare a variety of different network architectures across different data regimes both in terms of imitation performance as well as transfer to challenging locomotion tasks. Finally we show that it is possible to interleave the motion capture tracking with training on complementary tasks, enriching the resulting skill space, and enabling the reuse of skills not well covered by the motion capture data such as getting up from the ground or catching a ball.}
}