Learning to Schedule Control Fragments for Physics-Based Characters Using Deep Q-Learning
Lists
Only you see this
Abstract
Given a robust control system, physical simulation offers the potential for interactive human characters that move in realistic and responsive ways. In this article, we describe how to learn a scheduling scheme that reorders short control fragments as necessary at runtime to create a control system that can respond to disturbances and allows steering and other user interactions. These schedulers provide robust control of a wide range of highly dynamic behaviors, including walking on a ball, balancing on a bongo board, skateboarding, running, push-recovery, and breakdancing. We show that moderate-sized Q-networks can model the schedulers for these control tasks effectively and that those schedulers can be efficiently learned by the deep Q-learning algorithm.
BibTeX
@article{liu2017learning,
author = {Libin Liu and Jessica K. Hodgins},
title = {{Learning to Schedule Control Fragments for Physics-Based Characters Using Deep Q-Learning}},
journal = {ACM Trans. Graphics},
year = {2017},
doi = {10.1145/3083723},
}Loading related content...