Transform an encoded sequence of byte pair codeword IDs back into human-readable text. Parameters ----------

Check whether the graph contains cycles

Check if an `env`'s observation and action spaces are continuous. Parameters ---------- env : ``gym.wrappers`` or ``gym.envs`` insta

Check if the action and observation spaces for `env` are multidimensional or ``Tuple`` spaces. Notes ----- A multidimensional sp

Check that an array `X` is symmetric along its main diagonal

Check if the action and observation spaces for `env` are instances of ``gym.spaces.Tuple`` or ``gym.spaces.Dict``. Notes ----- A

Compute the LLB under the current GMM parameters.

Compute the log probability of a sequence of words under the unsmoothed, maximum-likelihood `N`-gram language model.

Return the embeddings associated with the IDs in `ids`. Parameters ---------- word_ids : :py:class:`ndarray <numpy.n

Computes the generator and critic loss using the WGAN-GP value function. Parameters ---------- Y_fake : :py:

Compute the NCE loss for a collection of inputs and associated targets. Parameters ---------- X : :py:class:`ndarray

Compute the magnitude spectrum (i.e., absolute value of the DFT spectrum) for each frame in `frames`. Assumes each frame is real-valued only.

Compute the Manhattan (`L1`) distance between two real vectors Notes ----- The Manhattan distance between two vectors **x** and **y*

Compute the log of the marginal likelihood (i.e., the log model evidence), :math:`p(y \mid X, \\text{kernel_params})`. Notes

Convert the mel-scale representation of a signal into Hz Parameters ---------- mel : :py:class:`ndarray <numpy.ndarray>` of shape `(

Apply the Mel-filterbank to the power spectrum for a signal `x`. Notes ----- The Mel spectrogram is the projection of the power spec

Compute the Mel-frequency cepstral coefficients (MFCC) for a signal. Notes ----- Computing MFCC features proceeds in the following s

A minibatch generator for skip-gram and CBOW models. Parameters ---------- corpus_fps : str or list of strs

Compute the Minkowski-`p` distance between two real vectors. Notes ----- The Minkowski-`p` distance between two vectors **x** and **

Return the top `n` most common tokens in the corpus

Computes the mean squared error between a policy's estimates of the expected arm payouts and the true expected payouts.

Get information on the observation space for `env`. Parameters ---------- env : ``gym.wrappers`` or ``gym.envs`` instance Th

Return the expected reward for an optimal agent. Parameters ---------- context : :py:class:`ndarray <numpy.ndarray>`

A fast, vectorized way to compute pairwise l2 distances between rows in `X` and `Y`. Notes ----- An entry of the pairwise Euclid

Check whether a path exists from vertex index `s_i` to `e_i`. Parameters ---------- s_i: Int The interal

Return the item with the largest/smallest (depending on ``self.heap_order``) priority *without* removing it from the queue.

Plot the cumulative reward per episode as a function of episode number. Notes ----- Saves plot to the file ``./img/<

Compute the power spectrum for a signal represented as a collection of frames. Assumes each frame is real-valued only. The power spectru

r""" Use the trained model to generate predictions for the distribution means, :math:`\mu`, associated with the collection of data poi

Use the trained classifier to predict the class label for each example in **X**. Parameters ---------- X: :p

Increase the amplitude of high frequency bands + decrease the amplitude of lower bands. Notes ----- Preemphasis filtering is (wa

"Pull" (i.e., sample from) a given arm's payoff distribution. Parameters ---------- arm_id : int The int

Run the agent on a single episode. Parameters ---------- max_steps : int The maximum number of steps to

r""" Compute a simple weighted average of the previous and current value. Notes ----- The smoothed value at timestep `t`, :math:`\til

Return all (state, action) pairs that have a nonzero probability of producing `outcome` under the current model. Parameters

returns num-tilings tile indices corresponding to the floats and ints

Return an adjacency dictionary representation of the graph

Convert the characters in `line` to a collection of bytes. Each byte is represented in decimal as an integer between 0 and 255. Paramete

Train a MAB policies on a multi-armed bandit problem, logging training statistics along the way. Parameters --------

Train the agent on a single episode. Parameters ---------- max_steps : int The maximum number of steps t

Convert a list of labels into a one-hot encoding. Parameters ---------- labels : list of length `N` A li

Generate the term-frequency inverse-document-frequency encoding of a text corpus. Parameters ---------- igno

Update the loss parameters using the accrued gradients and optimizer. Flush all gradients once the update is complete.

Update the parameters of the model online after each new state-action.

Update the priority queue with the most recent (state, action) pair and perform random-sample one-step tabular Q-planning. N

Compute parameter gradients for the critic on a single minibatch. Parameters ---------- X_real : :py:class:`ndarray

Compute parameter gradients for the generator on a single minibatch. Parameters ---------- X_shape : tuple of `(batc

Convert the words in `words` to their token indices. If a word is not in the vocabulary, return the index for the ``<unk>`` token

Perform a single contrastive divergence-`k` training update using the visible inputs `X` as a starting point for the Gibbs sampler.

The collection of layer inputs.

Currently broken

Initialize activation function

Initialize scheduler

Initialize the optimizer

Initialize weights according to the specified strategy

Apply the activation function to an input

Computes the generator and critic loss using the WGAN-GP value function. Parameters ---------- Y_fake : :py:

Generate random draws from the `probs` distribution over integers in [0, N). Parameters ---------- n_samples

Refer to documentation for the `_kernel` method

Assert whether `word` is a token in the vocabulary

Greater than or equal to

Return the value associated with key

Return the token (if key is an integer) or the index (if key is a string) for the key in the vocabulary, if it exists.

Greater than

A class for initializing activation functions. Valid `param` values are: (a) ``__str__`` representations of an `Activatio

A class for initializing learning rate schedulers. Valid `param` values are: (a) __str__ representations of `SchedulerBas

A class for initializing optimizers. Valid `param` values are: (a) __str__ representations of `OptimizerBase` instances