flatland.trajectories.trajectory_snapshot_callbacks module

flatland.trajectories.trajectory_snapshot_callbacks module#

class flatland.trajectories.trajectory_snapshot_callbacks.TrajectorySnapshotCallbacks(trajectory: Trajectory, data_dir_override: Path | None = None, snapshot_interval: int | None = None)[source]#

Bases: FlatlandCallbacks

FlatlandCallbacks to write env snapshots at the configured interval.

Parameters#

trajectory: Trajectory

the trajectory

data_dir_overridePath

use this override instead of the data_dir passed in the callback.

snapshot_intervalint

interval to write pkl snapshots to serialised_state subdirectory of the data_dir or data_dir_override. 1 means at every step. 0 means never.

on_episode_start(*, env: RailEnv | None = None, data_dir: Path | None = None, **kwargs) → None[source]#

Callback run right after an Episode has been started.

This method gets called after env.reset().

Parameters#

envEnvironment

the env

data_dirPath

trajectory data dir

kwargs:

Forward compatibility placeholder.

on_episode_step(*, env: RailEnv | None = None, data_dir: Path | None = None, **kwargs) → None[source]#

Called on each episode step (after the action(s) has/have been logged).

This callback is also called after the final step of an episode, meaning when terminated/truncated are returned as True from the env.step() call.

The exact time of the call of this callback is after env.step([action]) and also after the results of this step (observation, reward, terminated, truncated, infos) have been logged to the given episode object.

Parameters#

envEnvironment

the env

data_dirPath

trajectory data dir

kwargs:

Forward compatibility placeholder.

Contents