TrajectoryProcessor¶
-
class
maze.core.trajectory_recording.datasets.trajectory_processor.TrajectoryProcessor¶ Base class for processing individual trajectories.
-
static
convert_trajectory_with_env(trajectory: maze.core.trajectory_recording.records.trajectory_record.TrajectoryRecord, conversion_env: Optional[maze.core.env.maze_env.MazeEnv]) → List[maze.core.trajectory_recording.records.structured_spaces_record.StructuredSpacesRecord]¶ Convert an episode trajectory record into an array of observations and actions using the given env.
- Parameters
trajectory – Episode record to load
conversion_env – Env to use for conversion of MazeStates and MazeActions into observations and actions. Required only if state records are being loaded (i.e. conversion to raw actions and observations is needed).
- Returns
Loaded observations and actions. I.e., a tuple (observation_list, action_list). Each of the lists contains observation/action dictionaries, with keys corresponding to IDs of structured sub-steps. (I.e., the dictionary will have just one entry for non-structured scenarios.)
-
abstract
pre_process(trajectory: maze.core.trajectory_recording.records.trajectory_record.TrajectoryRecord) → Union[maze.core.trajectory_recording.records.trajectory_record.TrajectoryRecord, List[maze.core.trajectory_recording.records.trajectory_record.TrajectoryRecord]]¶ Preprocess a given trajectory before passing it through the wrapper stack.
In order to deal with pre-processing methods that create multiple trajectories from a single one (e.g. data augmentation by permutation of subsets) a single trajectory can be returned as well as a list of multiple trajectories.
- Parameters
trajectory – The trajectory to preprocess.
- Returns
The pre-processed trajectory or a list of multiple pre-processed trajectories.
-
process(trajectory: maze.core.trajectory_recording.records.trajectory_record.TrajectoryRecord, conversion_env: Optional[maze.core.env.maze_env.MazeEnv]) → List[List[maze.core.trajectory_recording.records.structured_spaces_record.StructuredSpacesRecord]]¶ Convert an individual trajectory, by calling the pre_processing method followed by the convert_trajectory_with_env
- Parameters
trajectory – Episode record to load.
conversion_env – Env to use for conversion of MazeStates and MazeActions into observations and actions. Required only if state records are being loaded (i.e. conversion to raw actions and observations is needed).
- Returns
A list (corresponding to the trajectories) of lists (corresponding to the steps of a individual trajectory) of Structured Spaces Records. Each Structures Spaces Record holds a single environment step with all corresponding information such as sub-step observations and actions as well as rewards and actor ids.
-
static