dynadojo.baselines.dnn.DNN#

class dynadojo.baselines.dnn.DNN#

Bases: AbstractAlgorithm

Deep Neural Network (DNN). Contains 5 hidden layers with 30 neurons each.

Methods

__init__(embed_dim, timesteps[, ...])

Initialize the class.

act(x, **kwargs)

Determines the control for each action horizon.

fit(x[, epochs, verbose])

Fits the algorithm on a tensor of trajectories.

predict(x0, timesteps, **kwargs)

Predict how initial conditions matrix evolves over a given number of timesteps.

Attributes

embed_dim

The embedded dimension of the dynamics.

max_control_cost

The maximum control cost.

seed

The random seed for the algorithm.

timesteps

The timesteps per training trajectory.
__init__(embed_dim, timesteps, max_control_cost=0, activation='relu', seed=None, **kwargs)#

Initialize the class.

Parameters:

  • embed_dim (int) – The embedded dimension of the system. Recommended to keep embed dimension small (e.g., <10).

  • timesteps (int) – The timesteps of the training trajectories. Must be greater than 2.

  • activation (str, optional) – The activation function used in the hidden layers. See tensorflow documentation for more details on acceptable activations. Defaults to relu.

  • max_control_cost (float, optional) – Ignores control, so defaults to 0.

  • **kwargs (dict, optional) – Additional keyword arguments

act(x, **kwargs)#

Determines the control for each action horizon. control.

Parameters:

  • x (numpy.ndarray) – (n, timesteps, embed_dim) Trajectories tensor.

  • **kwargs – Additional keyword arguments.

Returns:

(n, timesteps, embed_dim) controls tensor.

Return type:

numpy.ndarray

property embed_dim#

The embedded dimension of the dynamics.

fit(x, epochs=2000, verbose=0, **kwargs)#

Fits the algorithm on a tensor of trajectories.

Parameters:

  • x (np.ndarray) – (n, timesteps, embed_dim) Trajectories tensor.

  • **kwargs – Additional keyword arguments.

property max_control_cost#

The maximum control cost.

predict(x0, timesteps, **kwargs)#

Predict how initial conditions matrix evolves over a given number of timesteps.

Note

The timesteps argument can differ from the ._timesteps attribute. This allows algorithms to train on a dataset of a given size and then predict trajectories of arbitrary lengths.

Note

The first coordinate of each trajectory should match the initial condition x0.

Parameters:

  • x0 (np.ndarray) – (n, embed_dim) initial conditions matrix

  • timesteps (int) – timesteps per predicted trajectory

  • **kwargs – Additional keyword arguments.

Returns:

(n, timesteps, embed_dim) trajectories tensor

Return type:

np.ndarray

property seed#

The random seed for the algorithm.

property timesteps#

The timesteps per training trajectory.