avalanche.training.ReservoirSamplingBuffer

class avalanche.training.ReservoirSamplingBuffer(max_size: int)

Buffer updated with reservoir sampling.

__init__(max_size: int)

Parameters:

max_size –

Methods

__init__(max_size)	param max_size:
post_adapt(agent, exp)	Update buffer.
resize(strategy, new_size)	Update the maximum size of the buffer.
update(strategy, **kwargs)	Update self.buffer using the strategy state.
update_from_dataset(new_data)	Update the buffer using the given dataset.

Attributes

buffer	Buffer of samples.
max_size	Maximum size of the buffer.