|View source on GitHub|
Checkpoints data from Reverb replay buffer.
tf_agents.train.triggers.ReverbCheckpointTrigger( train_step: tf.Variable, interval: int, reverb_client:
How often, in train_steps, the trigger will save. Note that as
long as the >=
||the Reverb client required for checkpointing.|
reset() -> None
Resets the trigger interval.
set_start( start: int ) -> None
__call__( value: int, force_trigger: bool = False ) -> None
Maybe trigger the event based on the interval.
||the value for triggering.|
If True, the trigger will be forced triggered unless the
last trigger value is equal to