Tutorials¶

Step-by-step walkthroughs with screenshots of Arena. Each tutorial shows where to click and what you should see on screen.

Interactive tutorials on Home start from Start on a tutorial card. These written tutorials cover the same flows with screenshots.

Choose a tutorial¶

Tutorial	What you will do
Run your first Classic RL experiment	Create a Classic RL project, run the experiment wizard, train, open results
Create an Advanced Training project	Create a project with Advanced Training enabled and open Datasets
Upload a custom environment	Add custom gym code, set an entrypoint, validate
Upload a reasoning dataset	Create a reasoning dataset for Advanced Training
Upload an object detection dataset	Create a non-tabular object detection dataset with mask targets, then preprocess it (Enterprise)
Run an Advanced Training experiment (DPO)	Preference dataset + DPO through the wizard and start training
View results and checkpoints	Open metrics and checkpoint rows after a run
Deploy and invoke an agent	Deploy from a checkpoint and send a test prompt
Billing and credits	Read usage, plan, and credit balance (Manager)

Sign in to Arena with an account that can create projects in your organization.
Training runs spend training credits. The screenshots use sample org Acme Lab with stable demo data.