planar 2-link arm
Train Reacher with reinforcement learning
Gymnasium's planar two-link arm reaching for a target; trains in minutes.
- Actuators
- 2
- First skill
- 100K steps
- Size
- —
- License
- Gymnasium (MIT)
Tricks people teach Reacher
How it works
- Describe the trick in a sentence and pick Reacher.
- 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 Reacher to reach a target 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 Reacher without writing code?
Yes. Pick Reacher 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 Reacher need?
Roughly 100K 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 Reacher?
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 Reacher?
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 Reacher.