DeepMind Control Suite

The DeepMind Control Suite is a collection of 20 robotic manipulation tasks, each with 5 different environments and 5 different robot parameters. The tasks are designed to test the generalization capabilities of reinforcement learning agents.

Data and Resources

Cite this as

Tom Zahavy, Andre Barreto, Daniel J Mankowitz, Shaobo Hou, Brendan O'Donoghue, Iurii Kemaev, Satinder Singh (2024). Dataset: DeepMind Control Suite. https://doi.org/10.57702/1516z5s3

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2110.02497
Citation
  • https://doi.org/10.48550/arXiv.2102.04323
  • https://doi.org/10.48550/arXiv.2310.05086
  • https://doi.org/10.48550/arXiv.2102.08581
  • https://doi.org/10.48550/arXiv.2210.11698
  • https://doi.org/10.48550/arXiv.1801.00690
  • https://doi.org/10.48550/arXiv.2402.05421
  • https://doi.org/10.48550/arXiv.1907.02908
  • https://doi.org/10.48550/arXiv.2305.17400
  • https://doi.org/10.48550/arXiv.2210.09598
  • https://doi.org/10.48550/arXiv.2405.17009
Author Tom Zahavy
More Authors
Andre Barreto
Daniel J Mankowitz
Shaobo Hou
Brendan O'Donoghue
Iurii Kemaev
Satinder Singh
Homepage https://github.com/deepmind/dm_control