malt.agents.player.SequentialModelBasedPlayer
- class malt.agents.player.SequentialModelBasedPlayer(*args, **kwargs)[source]
Bases:
malt.agents.player.ModelBasedPlayer
Model based player with step size equal one.
Examples
>>> import malt >>> player = SequentialModelBasedPlayer( ... model = malt.models.supervised_model.SupervisedModel( ... representation=malt.models.representation.DGLRepresentation( ... out_features=128 ... ), ... regressor=malt.models.regressor.NeuralNetworkRegressor( ... in_features=128, ... ), ... ), ... policy=malt.policy.UtilityFunction(), ... trainer=malt.trainer.get_default_trainer(), ... merchant=malt.agents.merchant.DatasetMerchant( ... malt.data.collections.linear_alkanes(10), ... ), ... assayer=malt.agents.assayer.DatasetAssayer( ... malt.data.collections.linear_alkanes(10), ... ) ... )
>>> while True: ... if player.step() is None: ... break
Methods
__init__
(*args, **kwargs)assay
(dataset)merchandize
(dataset)prioritize
()step
()train
()