`stable_learning_control.algos.common.helpers`

Functions that are used in multiple Pytorch and TensorFlow algorithms.

Module Contents

`heuristic_target_entropy`(action_space)	Returns a heuristic target entropy for a given action space using the method
`get_activation_function`(activation_fn_name[, backend])	Get a given torch activation function.
`discount_cumsum`(x, discount)	Calculate the discounted cumsum.

`tf`
`tensorflow`

stable_learning_control.algos.common.helpers.heuristic_target_entropy(action_space)[source]

Returns a heuristic target entropy for a given action space using the method explained in Haarnoja et al. 2019.

Parameters:: action_space (:obj:`gym.spaces`) – The action space.
Raises:: NotImplementedError – If no heuristic target entropy has yet been implemented for the given action space.
Returns:: The target entropy.
Return type:: numpy.int64

stable_learning_control.algos.common.helpers.get_activation_function(activation_fn_name, backend='torch')[source]

Get a given torch activation function.

Parameters:

activation_fn_name (str) – The name of the activation function you want to retrieve.
backend (str) – The machine learning backend you want to use. Options are torch or tf2. By default torch.

Raises:

ValueError – Thrown if the activation function does not exist within the backend.

Returns:

The torch activation function.

Return type:

torch.nn.modules.activation

stable_learning_control.algos.common.helpers.discount_cumsum(x, discount)[source]

Calculate the discounted cumsum.