> For the complete documentation index, see [llms.txt](https://docs.roboset.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboset.org/quickstart/quickstart-1.md).
# Quickstart #1
### Contributor #1 - Training Platform
Goal: train your first robot policy and earn your first points.
1. Get access. The training platform is in private beta. Request an access code (DM @RobosetHQ) and go to roboset.org.
2. Sign in. Authenticate with your Google account. Your session maps to a Roboset trainer profile that tracks your episodes, models, rewards, and leaderboard position.
3. Pick a task. Choose one of the eight live tasks (start with Pick Stone or Move Cube — the easiest).
4. Choose a mode.
5. Train (RL): set an episode count and start automated PPO training. Watch reward, best reward, and success rate update live.
6. Demonstrate (Manual): take direct control of the arm and complete the task yourself. Your trajectory is recorded.
7. Save and evaluate. When training finishes, the model is saved to your account. Run an evaluation to score it on success rate, average reward, and closeness.
8. Earn. Points are credited for successful demos, completed runs, high-performance results, and evaluations. Check the Rewards page and your Leaderboard rank.
Next: try Hybrid mode — record a few demonstrations first, then start training. The policy warm-starts from your demos before RL fine-tunes it, usually producing better results faster.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.roboset.org/quickstart/quickstart-1.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.