consumer quadruped
Train Unitree Go2 with reinforcement learning
Unitree's robot dog from MuJoCo Menagerie (position-controlled variant), starting from its standing pose.
- Actuators
- 12
- First skill
- ~3M steps
- Size
- ≈40 cm tall
- License
- BSD-3-Clause
Tricks people teach Unitree Go2
How it works
- Describe the trick in a sentence and pick Unitree Go2.
- alia, kualia's assistant, writes the Gymnasium task — reward, success, failure and world objects — and runs 13 automatic checks.
- Train with PPO on kualia's servers and watch every checkpoint replayed in 3D in your browser.
- Export a deterministic ONNX policy and run it on the robot with onnxruntime.
From your coding agent
Working in Claude Code, Cursor or Codex? Connect kualia as an MCP server with a personal API key (Settings → API keys), then ask: “Train my Unitree Go2 to trot forward with kualia.”
claude mcp add --transport http kualia https://kualia.ai/api/mcp \ --header "Authorization: Bearer $KUALIA_API_KEY"Coding-agent guide →
Questions
Can I train Unitree Go2 without writing code?
Yes. Pick Unitree Go2 in kualia, describe the trick in a sentence, and kualia's assistant writes the Gymnasium task (reward, success, failure and any world objects), runs 13 automatic checks and trains a PPO policy in MuJoCo.
How many training steps does Unitree Go2 need?
Roughly ~3M steps for a first real skill with PPO. Start with a 10,000-step first try to check the task before spending more.
Can I run the trained policy on the real Unitree Go2?
kualia exports a deterministic ONNX policy with observation normalisation baked in, plus metadata describing observations and action scaling. You run it with onnxruntime on the robot's computer. Test carefully: simulation and hardware differ.
Can my coding agent use kualia for Unitree Go2?
Yes. kualia is a remote MCP server at https://kualia.ai/api/mcp. Add it to Claude Code, Cursor or Codex with a personal API key and ask the agent to train Unitree Go2.
More bigger real robots
Unitree Go2 model by Unitree, BSD-3-Clause; used unchanged except for a floor, a standing pose and actuator centring where noted. kualia is not affiliated with Unitree.