SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1801.00690 · 2018

DeepMind Control Suite

David Budden, Josh Merel, Yazhe Li, Yuval Tassa, Martin Riedmiller, Las Casas, Diego De, Timothy Lillicrap, Yotam Doron, Alistair Muldal, Tom Erez, Abbas Abdolmaleki, and 1 more

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1801.00690")
get_code_for_paper("1801.00690")
have("1801.00690")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1801.00690.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1801.00690.svg)](https://syntology.ai/paper/1801.00690)

Connect an agent — have() is free.