stable_learning_control.algos.pytorch.policies.critics

Critic network structures.

Submodules

Package Contents

Classes

LCritic

Soft Lyapunov critic Network.

QCritic

Soft Q critic network.
class stable_learning_control.algos.pytorch.policies.critics.LCritic(obs_dim, act_dim, hidden_sizes, activation=nn.ReLU)[source]

Bases: torch.nn.Module

Soft Lyapunov critic Network.

L

The layers of the network.

Type:

torch.nn.Sequential

Initialise the LCritic object.

Parameters:

  • obs_dim (int) – Dimension of the observation space.

  • act_dim (int) – Dimension of the action space.

  • hidden_sizes (list) – Sizes of the hidden layers.

  • activation (torch.nn.modules.activation, optional) – The activation function. Defaults to torch.nn.ReLU.

forward(obs, act)[source]

Perform forward pass through the network.

Parameters:
Returns:

The tensor containing the lyapunov values of the input observations and actions.

Return type:

torch.Tensor

class stable_learning_control.algos.pytorch.policies.critics.QCritic(obs_dim, act_dim, hidden_sizes, activation=nn.ReLU, output_activation=nn.Identity)[source]

Bases: torch.nn.Module

Soft Q critic network.

Q

The layers of the network.

Type:

torch.nn.Sequential

Initialise the QCritic object.

Parameters:

  • obs_dim (int) – Dimension of the observation space.

  • act_dim (int) – Dimension of the action space.

  • hidden_sizes (list) – Sizes of the hidden layers.

  • activation (torch.nn.modules.activation, optional) – The activation function. Defaults to torch.nn.ReLU.

  • output_activation (torch.nn.modules.activation, optional) – The activation function used for the output layers. Defaults to torch.nn.Identity.

forward(obs, act)[source]

Perform forward pass through the network.

Parameters:
Returns:

The tensor containing the Q values of the input observations and actions.

Return type:

torch.Tensor