garage.torch.value_functions.value_function module

Base class for all baselines.

class ValueFunction(env_spec, name)[source]

Bases: abc.ABC, sphinx.ext.autodoc.importer._MockObject

Base class for all baselines.

Parameters:
compute_loss(obs, returns)[source]

Compute mean value of loss.

Parameters:
  • obs (torch.Tensor) – Observation from the environment with shape \((N \dot [T], O*)\).
  • returns (torch.Tensor) – Acquired returns with shape \((N, )\).
Returns:

Calculated negative mean scalar value of

objective (float).

Return type:

torch.Tensor