> ## Documentation Index
> Fetch the complete documentation index at: https://icrl.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Batch Training

> Train and evaluate across many goals

## Python

```python theme={null}
trajectories = await agent.train_batch(env_factory, goals)
results = await agent.run_batch(env_factory, eval_goals)
```

`env_factory` should return a fresh environment instance per goal.

## TypeScript

```ts theme={null}
const trajectories = await agent.trainBatch(envFactory, goals);
const results = await agent.runBatch(envFactory, evalGoals);
```

## Suggested Workflow

1. Build a curriculum of goals.
2. Train in rounds.
3. Evaluate with `run`/`runBatch` on held-out goals.
4. Monitor DB stats and curation behavior.

## Validation

Python DB includes deferred validation methods (`validate_trajectory`, `validate_all`) that can be run post-training for code-change persistence checks.