RoboHive
- Software
- Humanoids and robot learning
- Framework
A collection of robot manipulation and locomotion environments simulated in the MuJoCo physics engine and exposed through the OpenAI Gym API, for training learning agents.
- Stale
Source on GitHub: github.com/vikashplus/robohive (opens in a new tab). Facts read at commit 6c14798 (opens in a new tab).
Licenses
- Code
- Apache-2.0 (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (Apache-2.0) at commit 6c14798 (opens in a new tab), on 22 Oct 2026.
- Commercial use
- Yes
Labels
- StaleNo commit in 12 months: the newest is from 26 Mar 2024.
What it does
- Provides simulated tasks grouped into suites, including dexterous hand manipulation, arm manipulation, musculoskeletal control and multi-task benchmarks.
- Works with gym-compatible agent training frameworks such as Stable Baselines, RLlib and TorchRL.
- Installs via pip, with an initialization command and a demo script that runs a Franka reach environment.
- Some suites are listed as work in progress or coming soon, such as the TCDM and ROBEL suites.
- Includes visual encoder options such as R3M, RRL and VC, set up through detailed installation instructions.
Written by Robotheca from the project's README (opens in a new tab) at commit 6c14798.
Getting started
- Difficulty
- Advanced
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Stale: no commit in 12 months
- Newest commit
- 26 Mar 2024 on main
- Latest release
- None published on GitHub
Checked on GitHub on 22 Oct 2026.
Links
Robots that can run it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.