# tinker_cookbook.rl.trajectory_to_data

### [**tinker_cookbook.rl.trajectory_to_data**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/rl/data_processing.py#L95)(*traj*, *traj_advantage*)

Return one or more Datum objects corresponding to the trajectory.

If the sequence grows by appending, i.e., each successive observation contains the previous observation+action as a prefix, then we can return a single Datum. However, if we get a sequence that's not an extension of the previous sequence, then that results in a new Datum.

For example, let O1 denote a chunk of observation tokens, and let A1 denote an action.

Then let's say ob_ac_pairs is as follows.

(O1, A1) (O1+A1+O2, A2) (O3, A3)

Then we will merge the first two observation-action pairs into a single Datum, and the last observation-action pair into a separate Datum.

**Parameters:**

- [**traj**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/rl/data_processing.py#L95) (*[Trajectory](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/rl/trajectory/index.md)*) – A single trajectory containing transitions (observation-action pairs).
- [**traj_advantage**](https://github.com/thinking-machines-lab/tinker-cookbook/blob/main/tinker_cookbook/rl/data_processing.py#L95) (*float*) – The scalar advantage to assign to all action tokens in this trajectory.

**Returns:** *list\[tinker.[Datum](https://tinker-docs.thinkingmachines.ai/tinker/api-reference/types/datum/index.md)\]* – One or more training datums, each containing model input, targets, sampled log-probs, advantages, and masks.

## Referenced by

- [tinker_cookbook.rl.InitialObservationOverflow](https://tinker-docs.thinkingmachines.ai/cookbook/api-reference/rl/initialobservationoverflow/index.md)