Rate this Page

Offline RL Methods#

Loss modules for offline reinforcement learning.

CQLLoss(*args, **kwargs)

TorchRL implementation of the continuous CQL loss.

DiscreteCQLLoss(*args, **kwargs)

TorchRL implementation of the discrete CQL loss.

IQLLoss(*args, **kwargs)

TorchRL implementation of the IQL loss.

DiscreteIQLLoss(*args, **kwargs)

TorchRL implementation of the discrete IQL loss.

TD3BCLoss(*args, **kwargs)

TD3+BC Loss Module.