Experiment wizard overview

New and draft experiments use a stepper. Classic RL has six steps; Advanced Training has five (no HPO). The header is a horizontal stepper; the body swaps content as you move.

Steps (in order)

1. Resources: Training cluster (nodes, GPU class, GPU size, GPU count).

2. Environment: gym (classic) or gym / dataset (Advanced Training).

3. Agent: algorithm and model or network.

4. Training: rollout length, batch sizes, and related fields.

5. HPO (Classic RL only): hyperparameter optimization.

6. Summary: read-only review; Train or Resume here.

Advanced Training omits HPO. After Training, Next goes to Summary.

Classic vs Advanced Training

When you created the project, the Training switcher set the type:

• Classic RL: gym environment grid, standard Agent form, classic Training accordions. After Training, continue to HPO, then Summary.

• Advanced Training: combined environment grid (datasets and RL Environment rows), Pipelines tab on the project, and LLM-oriented agent and training UI where the flow needs it. There is no HPO step; HPO stays off and cannot be turned on. After Training, continue to Summary.

See Projects.

Navigation

Back and Next appear on every step except Summary, which has Back plus Train or Resume.

On a Draft, Next is disabled until the step is complete. A blocked banner states the reason (no training cluster, no environment, no algorithm, form errors, reward validation not finished, bad prompt template, and similar).

On a non-draft experiment you can click step names to review configuration.

Save appears only on Summary (with Train or Resume) for Draft experiments that already have a training cluster. It keeps the draft without scheduling training. Mid-steps use Next and idle autosave instead.

After Resources, you can change compute later with Edit resources (opens Select training cluster) from later wizard steps.

A draft also saves on its own after about five minutes of idle activity (mouse, keyboard, scroll, or click). Success toasts look like Updated draft experiment: {name} or Created draft experiment: {name}.

Summary step

On Summary for a draft, Train schedules the run. Tooltip: training begins shortly when resources are ready, usually within about ten minutes. Status becomes Pending first; allow up to roughly ten minutes for the job to move to Running when the cluster is busy. Success toast: Experiment {name} scheduled for training…

If the experiment is no longer a Draft, Resume replaces Train (unless status is Running or Pending). Resume opens a dialog to pick a checkpoint and name a new experiment.

After a successful Train from the wizard, Arena returns you to the project Experiments tab and the stepper resets to Resources.

Step guides

Wizard step	Guide
Resources	Choosing compute
Environment	Environment step
Agent	Agent step
Training	Training step
HPO (Classic RL)	Hyperparameter search

After training, see Experiment statuses.