allenact.embodiedai.aux_losses.losses
#
Defining the auxiliary loss for actor critic type models.
Several of the losses defined in this file are modified versions of those found in https://github.com/joel99/habitat-pointnav-aux/blob/master/habitat_baselines/
MultiAuxTaskNegEntropyLoss
#
class MultiAuxTaskNegEntropyLoss(AbstractActorCriticLoss)
Used in multiple auxiliary tasks setting. Add a negative entropy loss over all the task weights.
AuxiliaryLoss
#
class AuxiliaryLoss(AbstractActorCriticLoss)
Base class of auxiliary loss.
Any auxiliary task loss should inherit from it, and implement
the get_aux_loss
function.
InverseDynamicsLoss
#
class InverseDynamicsLoss(AuxiliaryLoss)
Auxiliary task of Inverse Dynamics from Auxiliary Tasks Speed Up Learning PointGoal Navigation (Ye, 2020) https://arxiv.org/abs/2007.04561 originally from Curiosity-driven Exploration by Self-supervised Prediction (Pathak, 2017) https://arxiv.org/abs/1705.05363
InverseDynamicsLoss.__init__
#
| __init__(subsample_rate: float = 0.2, subsample_min_num: int = 10, *args, **kwargs)
Subsample the valid samples by the rate of subsample_rate
,
if the total num of the valid samples is larger than subsample_min_num
.
TemporalDistanceLoss
#
class TemporalDistanceLoss(AuxiliaryLoss)
Auxiliary task of Temporal Distance from Auxiliary Tasks Speed Up Learning PointGoal Navigation (Ye, 2020) https://arxiv.org/abs/2007.04561
CPCALoss
#
class CPCALoss(AuxiliaryLoss)
Auxiliary task of CPC|A from Auxiliary Tasks Speed Up Learning PointGoal Navigation (Ye, 2020) https://arxiv.org/abs/2007.04561 originally from Neural Predictive Belief Representations (Guo, 2018) https://arxiv.org/abs/1811.06407