Shortcuts

CountFramesLog

class torchrl.trainers.CountFramesLog(*args, **kwargs)[source]

A frame counter hook.

Parameters:
  • frame_skip (int) – frame skip of the environment. This argument is important to keep track of the total number of frames, not the apparent one.

  • log_pbar (bool, optional) – if True, the reward value will be logged on the progression bar. Default is False.

Examples

>>> count_frames = CountFramesLog(frame_skip=frame_skip)
>>> trainer.register_op("pre_steps_log", count_frames)
register(trainer: Trainer, name: str = 'count_frames_log')[source]

Registers the hook in the trainer at a default location.

Parameters:
  • trainer (Trainer) – the trainer where the hook must be registered.

  • name (str) – the name of the hook.

Note

To register the hook at another location than the default, use register_op().

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources