dm_control: Software and Tasks for Continuous Control
Yuval Tassa
S. Tunyasuvunakool
Alistair Muldal
Yotam Doron
Piotr Trochim
Siqi Liu
Steven Bohez
J. Merel
Tom Erez
Timothy Lillicrap
N. Heess

Abstract
The dm_control software package is a collection of Python libraries and task suites for reinforcement learning agents in an articulated-body simulation. A MuJoCo wrapper provides convenient bindings to functions and data structures. The PyMJCF and Composer libraries enable procedural model manipulation and task authoring. The Control Suite is a fixed set of tasks with standardised structure, intended to serve as performance benchmarks. The Locomotion framework provides high-level abstractions and examples of locomotion tasks. A set of configurable manipulation tasks with a robot arm and snap-together bricks is also included. dm_control is publicly available at https://www.github.com/deepmind/dm_control
View on arXivComments on this paper