# tinker_cookbook.rl.RLDataset

## *class* [**tinker_cookbook.rl.RLDataset**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/rl/types.py#L445)(*ABC*)

A dataset that produces batches of [`EnvGroupBuilder`](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/rl/envgroupbuilder/index.md) instances.

This is the primary dataset interface consumed by RL training loops. Implementations must define `get_batch` and `__len__`.

```python
class MyDataset(RLDataset):
def __init__(self, builders: list[EnvGroupBuilder], batch_size: int):
self.builders = builders
self.batch_size = batch_size
def get_batch(self, index: int) -> Sequence[EnvGroupBuilder]:
start = index * self.batch_size
return self.builders[start : start + self.batch_size]
def __len__(self) -> int:
return len(self.builders) // self.batch_size
```

### [**get_batch**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/rl/types.py#L467)(*index*)

Return a batch of EnvGroupBuilder instances at the given index.

**Parameters:**

- [**index**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/rl/types.py#L467) (*int*) – The batch index (`0 <= index < len(self)`).

**Returns:** *Sequence\[[EnvGroupBuilder](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/rl/envgroupbuilder/index.md)\]* – The environment group builders for this batch.

*Abstract method.*

## Referenced by

- [tinker_cookbook.distillation.PromptOnlyDataset](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/distillation/promptonlydataset/index.md)
- [tinker_cookbook.rl.RLDatasetBuilder.__call__](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/rl/rldatasetbuilder/#rldatasetbuilder-call)