Evolvable Multi-layer Perceptron (MLP)¶
Parameters¶
- class agilerl.networks.evolvable_mlp.EvolvableMLP(num_inputs: int, num_outputs: int, hidden_size: List[int], feature_hidden_size=[128], num_atoms=51, mlp_activation='ReLU', mlp_output_activation=None, min_hidden_layers=1, max_hidden_layers=3, min_mlp_nodes=64, max_mlp_nodes=500, layer_norm=True, output_vanish=True, init_layers=True, support=None, rainbow=False, device='cpu', accelerator=None, arch='mlp')¶
The Evolvable Multi-layer Perceptron class.
- Parameters:
num_inputs (int) – Input layer dimension
num_outputs (int) – Output layer dimension
feature_hidden_size (list[int]) – Hidden size for the feature network when using Rainbow DQN, defaults to [128]
num_atoms (int, optional) – Number of atoms for Rainbow DQN, defaults to 51
mlp_activation (str, optional) – Activation layer, defaults to ‘relu’
mlp_output_activation (str, optional) – Output activation layer, defaults to None
min_hidden_layers (int, optional) – Minimum number of hidden layers the network will shrink down to, defaults to 1
max_hidden_layers (int, optional) – Maximum number of hidden layers the network will expand to, defaults to 3
min_mlp_nodes (int, optional) – Minimum number of nodes a layer can have within the network, defaults to 64
max_mlp_nodes (int, optional) – Maximum number of nodes a layer can have within the network, defaults to 500
layer_norm (bool, optional) – Normalization between layers, defaults to True
output_vanish (bool, optional) – Vanish output by multiplying by 0.1, defaults to True
init_layers (bool, optional) – Initialise network layers, defaults to True
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_mlp_layer()¶
Adds a hidden layer to neural network.
- add_mlp_node(hidden_layer=None, numb_new_nodes=None)¶
Adds nodes to hidden layer of neural network.
- clone()¶
Returns clone of neural net with identical parameters.
- create_mlp(input_size, output_size, hidden_size, output_vanish, output_activation, noisy=False, rainbow_feature_net=False)¶
Creates and returns multi-layer perceptron.
- create_net()¶
Creates and returns neural network.
- forward(x, q=True)¶
Returns output of neural network.
- Parameters:
x (torch.Tensor() or np.array) – Neural network input
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
- property init_dict¶
Returns model information in dictionary.
- 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.
- remove_mlp_layer()¶
Removes a hidden layer from neural network.
- remove_mlp_node(hidden_layer=None, numb_new_nodes=None)¶
Removes nodes from hidden layer of neural network.
- 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