dm_control: Software and tasks for continuous control
Saran Tunyasuvunakool, Alistair Muldal, Yotam Doron et al. · Software Impacts · 2020
The dm_control software package is a collection of Python libraries and task suites for reinforcement learning agents in an articulated-body simulation. Infrastructure includes a wrapper for the MuJoCo physics engine and libraries for procedural model manipulation and task authoring. Task suites include the Control Suite, a set of standardized tasks intended to serve as performance benchmarks, a locomotion framework and task families, and a set of manipulation tasks with a robot arm and snap-together bricks. An adjunct tech report and interactive tutorial are also provided.
Cited by 199 works. doi:10.1016/j.simpa.2020.100022 Open-access PDF
Authors
- Saran Tunyasuvunakool
- Alistair Muldal
- Yotam Doron
- Siqi Liu
- Steven Bohez
- Josh Merel
- Tom Erez
- Timothy Lillicrap
- Nicolas Heess
- Yuval Tassa
References
- Reinforcement Learning: An Introduction
- Human-level control through deep reinforcement learning
- Mastering the game of Go with deep neural networks and tree search
- Dynamic Programming and Optimal Control
- Neuronlike adaptive elements that can solve difficult learning control problems
- Continuous control with deep reinforcement learning
- Proceedings of the 24th international conference on Machine learning
- Reinforcement Learning: An Introduction
- MuJoCo: A physics engine for model-based control
- Trust Region Policy Optimization