pyhgf.typing.typing.UpdateSequence#

class pyhgf.typing.typing.UpdateSequence(prediction_steps, update_steps, pre_prediction_steps=None, post_update_steps=None, action_steps=None)[source]#

Set of update functions to apply to the network.

Parameters:

  • prediction_steps (tuple[tuple[int, jaxlib.xla_extension.PjitFunction], ...]) – The sequence of prediction steps applied top-down before observation.

  • update_steps (tuple[tuple[int, jaxlib.xla_extension.PjitFunction], ...]) – The sequence of posterior and prediction-error update steps.

  • pre_prediction_steps (tuple[tuple[int, jaxlib.xla_extension.PjitFunction], ...] | None) – Optional steps applied before the prediction steps.

  • post_update_steps (tuple[tuple[int, jaxlib.xla_extension.PjitFunction], ...] | None) – Optional steps applied after the update steps.

  • action_steps (tuple[tuple[int, jaxlib.xla_extension.PjitFunction], ...] | None) – Optional steps implementing an agent’s action selection.

__init__(*args, **kwargs)#

Methods

__init__(*args, **kwargs)

count(value, /)

Return number of occurrences of value.

index(value[, start, stop])

Return first index of value.

Attributes

action_steps

Alias for field number 4

post_update_steps

Alias for field number 3

pre_prediction_steps

Alias for field number 2

prediction_steps

Alias for field number 0

update_steps

Alias for field number 1