Make Evolvable

Parameters

class agilerl.wrappers.make_evolvable.MakeEvolvable(network, input_tensor, secondary_input_tensor=None, num_atoms=51, min_hidden_layers=1, max_hidden_layers=3, min_mlp_nodes=64, max_mlp_nodes=1024, min_cnn_hidden_layers=1, max_cnn_hidden_layers=6, min_channel_size=32, max_channel_size=256, output_vanish=False, init_layers=False, support=None, rainbow=False, device='cpu', accelerator=None, **kwargs)

Wrapper to make a neural network evolvable

Parameters:

  • network (nn.Module) – Input neural network

  • input_tensor (torch.Tensor) – Example input tensor so forward pass can be made to detect the network architecture

  • num_atoms (int, optional) – Number of atoms for Rainbow DQN, defaults to 51

  • secondary_input_tensor (torch.Tensor, optional) – Second input tensor if network performs forward pass with two tensors, for example, off-policy algorithms that use a critic(s) with environments that have RGB image observations and thus require CNN architecture, defaults to None

  • min_hidden_layers (int, optional) – Minimum number of hidden layers the fully connected layer will shrink down to, defaults to 1

  • max_hidden_layers (int, optional) – Maximum number of hidden layers the fully connected layer will expand to, defaults to 3

  • min_mlp_nodes (int, optional) – Minimum number of nodes a layer can have within the fully connected layer, defaults to 64

  • max_mlp_nodes (int, optional) – Maximum number of nodes a layer can have within the fully connected layer, defaults to 1024

  • min_cnn_hidden_layers (int, optional) – Minimum number of hidden layers the convolutional layer will shrink down to, defaults to 1

  • max_cnn_hidden_layers (int, optional) – Maximum number of hidden layers the convolutional layer will expand to, defaults to 6

  • min_channel_size (int, optional) – Minimum number of channels a convolutional layer can have, defaults to 32

  • max_channel_size (int, optional) – Maximum number of channels a convolutional layer can have, defaults to 256

  • output_vanish (bool, optional) – Vanish output by multiplying by 0.1, defaults to False

  • init_layers (bool, optional) – Initialise network layers, defaults to False

  • support (torch.Tensor(), optional) – Atoms support tensor, defaults to None

  • rainbow (bool, optional) – Using Rainbow DQN, defaults to False

  • device (str, optional) – Device for accelerated computing, ‘cpu’ or ‘cuda’, defaults to ‘cpu’

  • accelerator (accelerate.Accelerator(), optional) – Accelerator for distributed computing, defaults to None

add_cnn_channel(hidden_layer=None, numb_new_channels=None)

Adds channel to hidden layer of Convolutional Neural Network.

Parameters:

  • hidden_layer (int, optional) – Depth of hidden layer to add channel to, defaults to None

  • numb_new_channels (int, optional) – Number of channels to add to hidden layer, defaults to None

add_cnn_layer()

Adds a hidden layer to convolutional neural network.

add_mlp_layer()

Adds a hidden layer to value network.

add_mlp_node(hidden_layer=None, numb_new_nodes=None)

Adds nodes to hidden layer of value network.

Parameters:

  • hidden_layer (int, optional) – Depth of hidden layer to add nodes to, defaults to None

  • numb_new_nodes (int, optional) – Number of nodes to add to hidden layer, defaults to None

calc_max_kernel_sizes()

Calculates the max kernel size for each convolutional layer of the feature net.

calc_stride_size_ranges()

Calculates a range of stride sizes for each convolutional layer of the feature net.

change_cnn_kernel()

Randomly alters convolution kernel of random CNN layer.

clone()

Returns clone of neural net with identical parameters.

create_cnn(input_size, channel_size, kernel_size, stride_size, padding, name)

Creates and returns convolutional neural network.

Parameters:

  • input_size (int) – Channel size of first layer

  • channel_size (list[int]) – Output channel sizes for each layer

  • kernel_size (list[int] or list[Tuple[int]]) – Kernel sizes

  • stride_size (list[int] or list[Tuple[int]]) – Stride sizes

  • padding (list[int] or list[Tuple[int]]) – Convolutional layer padding

  • name (str) – Layer name

create_mlp(input_size, output_size, hidden_size, name, mlp_activation, mlp_output_activation, noisy=False, rainbow_feature_net=False)

Creates and returns multi-layer perceptron.

Parameters:

  • input_size (int) – Input dimensions to first MLP layer

  • output_size (int) – Output dimensions from last MLP layer

  • hidden_size (list[int]) – Hidden layer sizes

  • name (str) – Layer name

Parameters:

rainbow_feature_net

create_nets()

Creates and returns the feature and value net.

detect_architecture(network, input_tensor, secondary_input_tensor=None)

Detect the architecture of a neural network.

Parameters:

  • network (nn.Module) – Neural network whose architecture is being detected

  • input_tensor (torch.Tensor) – Tensor used to perform forward pass to detect layers

  • secondary_input_tensor – Second tensor used to perform forward pass if forward

method of neural network takes two tensors as arguments, defaults to None :type secondary_input_tensor: torch.Tensor, optional

forward(x, xc=None, q=True)

Returns output of neural network.

Parameters:

  • x (torch.Tensor() or np.array) – Neural network input

  • xc (torch.Tensor() or np.array, optional) – Actions to be evaluated by critic, defaults to None

  • q (bool, optional) – Return Q value if using rainbow, defaults to True

get_activation(activation_names)

Returns activation function for corresponding activation name.

Parameters:

activation_names (str) – Activation function name

get_conv_layer(conv_layer_name, in_channels, out_channels, kernel_size, stride, padding)

Return convolutional layer for corresponding convolutional layer name.

Parameters:

  • conv_layer_name (str) – Convolutional layer name

  • in_channels (int) – Number of input channels to convolutional layer

  • out_channels (int) – Number of output channels from convolutional layer

  • kernel_size (int or Tuple[int]) – Kernel size of convolutional layer

  • stride (int or Tuple[int]) – Stride size of convolutional layer

  • padding (int or Tuple[int]) – Convolutional layer padding

get_normalization(normalization_name, layer_size)

Returns normalization layer for corresponding normalization name.

Parameters:

  • normalization_names (str) – Normalization layer name

  • layer_size – The layer after which the normalization layer will be applied

  • layer_size – int

get_pooling(pooling_names, kernel_size, stride, padding)

Returns pooling layer for corresponding activation name.

Parameters:

  • pooling_names (str) – Pooling layer name

  • kernel_size (int or Tuple[int]) – Pooling layer kernel size

  • stride (int or Tuple[int]) – Pooling layer stride

  • padding (int or Tuple[int]) – Pooling layer padding

property init_dict

Returns model information in dictionary.

layer_init(layer, std=1.4142135623730951, bias_const=0.0)

Initialize the weights of a neural network layer using orthogonal initialization and set the biases to a constant value.

Parameters:

  • layer (nn.Module) – Neural network layer

  • std (float) – Standard deviation, defaults to sqrt(2)

  • bias_const (float) – Bias value, defaults to 0.0

preserve_parameters(old_net, new_net)

Returns new neural network with copied parameters from old network.

Parameters:

  • old_net (nn.Module()) – Old neural network

  • new_net (nn.Module()) – New neural network

recreate_nets(shrink_params=False)

Recreates neural networks.

Parameters:

shrink_params (bool) – Boolean flag to shrink parameters

remove_cnn_channel(hidden_layer=None, numb_new_channels=None)

Remove channel from hidden layer of convolutional neural network.

Parameters:

  • hidden_layer (int, optional) – Depth of hidden layer to add channel to, defaults to None

  • numb_new_channels (int, optional) – Number of channels to add to hidden layer, defaults to None

remove_cnn_layer()

Removes a hidden layer from the convolutional neural network.

remove_mlp_layer()

Removes a hidden layer from value network.

remove_mlp_node(hidden_layer=None, numb_new_nodes=None)

Removes nodes from hidden layer of neural network.

Parameters:

  • hidden_layer (int, optional) – Depth of hidden layer to remove nodes from, defaults to None

  • numb_new_nodes (int, optional) – Number of nodes to remove from hidden layer, defaults to None

reset_noise()

Resets noise of value and advantage networks.

shrink_preserve_parameters(old_net, new_net)

Returns shrunk new neural network with copied parameters from old network.

Parameters:

  • old_net (nn.Module()) – Old neural network

  • new_net (nn.Module()) – New neural network