Booster Soccer Showdown policies
- AI model
- Humanoids and robot learning
A robotics soccer competition toolkit for Booster T1 robots, built around generalization across environments, with teleoperation, motion tools and a DDPG training pipeline.
Made by ArenaX Labs.
Source on GitHub: github.com/ArenaX-Labs/booster_soccer_showdown (opens in a new tab). Facts read at commit 628f08e (opens in a new tab).
Licenses
- Code
- MIT (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit 628f08e (opens in a new tab), on 16 Oct 2026.
- Weights
- MIT (opens in a new tab)
Read on huggingface.co/SaiResearch/booster_soccer_models (opens in a new tab).
- Commercial use
- Yes
What it does
- Provides keyboard teleoperation of simulated Booster robots in several penalty-kick and kick-to-target environments.
- Offers mimic tools that compute kinematic signals from motion files and replay motions in the MuJoCo viewer.
- Includes a minimal DDPG reinforcement learning pipeline with actor and critic networks, replay buffer and exploration noise.
- Entry-point script builds the environment via the SAI client, trains the model, then supports watching and benchmarking.
- Includes a script to test a pretrained model on a chosen environment.
- Models and datasets are hosted on Hugging Face, and the competition runs on SAI.
Written by Robotheca from the project's README (opens in a new tab) at commit 628f08e.
Getting started
- Difficulty
- Advanced
- How to start
- The project's README (opens in a new tab)
Maintenance
- Status
- Maintained: a commit in the last 12 months
- Newest commit
- 19 Nov 2025 on main
- Latest release
- None published on GitHub
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use 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 AI models as a reference: nothing is hosted or run here, and every fact links to where it was read.