DeepMind Control Suite

Author(s)
Tassa, Yuval
Doron, Yotam
Muldal, Alistair
Erez, Tom
Li, Yazhe
Casas, Diego de Las
Budden, David
Abdolmaleki, Abbas
Merel, Josh
Lefrancq, Andrew
Keywords
Computer Science - Artificial Intelligence

Full record
Show full item record
URI
http://hdl.handle.net/20.500.12424/2495668
Online Access
http://arxiv.org/abs/1801.00690
Abstract
The DeepMind Control Suite is a set of continuous control tasks with a standardised structure and interpretable rewards, intended to serve as performance benchmarks for reinforcement learning agents. The tasks are written in Python and powered by the MuJoCo physics engine, making them easy to use and modify. We include benchmarks for several learning algorithms. The Control Suite is publicly available at https://www.github.com/deepmind/dm_control . A video summary of all tasks is available at http://youtu.be/rAai4QzcYbs .
Comment: 24 pages, 7 figures, 2 tables
Date
2018-01-02
Type
text
Identifier
oai:arXiv.org:1801.00690
http://arxiv.org/abs/1801.00690
Collections