Shortcuts

AdditiveGaussianWrapper

class torchrl.modules.tensordict_module.AdditiveGaussianWrapper(*args, **kwargs)[source]

Additive Gaussian PO wrapper.

Parameters:

policy (TensorDictModule) – a policy.

Keyword Arguments:
  • sigma_init (scalar, optional) – initial epsilon value. default: 1.0

  • sigma_end (scalar, optional) – final epsilon value. default: 0.1

  • annealing_num_steps (int, optional) – number of steps it will take for sigma to reach the sigma_end value.

  • mean (float, optional) – mean of each output element’s normal distribution.

  • std (float, optional) – standard deviation of each output element’s normal distribution.

  • action_key (NestedKey, optional) – if the policy module has more than one output key, its output spec will be of type CompositeSpec. One needs to know where to find the action spec. Default is “action”.

  • spec (TensorSpec, optional) – if provided, the sampled action will be projected onto the valid action space once explored. If not provided, the exploration wrapper will attempt to recover it from the policy.

  • safe (boolean, optional) – if False, the TensorSpec can be None. If it is set to False but the spec is passed, the projection will still happen. Default is True.

Note

Once an environment has been wrapped in AdditiveGaussianWrapper, it is crucial to incorporate a call to step() in the training loop to update the exploration factor. Since it is not easy to capture this omission no warning or exception will be raised if this is ommitted!

forward(tensordict: TensorDictBase) TensorDictBase[source]

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

step(frames: int = 1) None[source]

A step of sigma decay.

After self.annealing_num_steps, this function is a no-op.

Parameters:

frames (int) – number of frames since last step.

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources