Return order T,H,W,C { 0: { 'rgb': (T,H,W,C), 'timestamp': (T,) },

Update this config using another config or nested dictionary.

A context scope for modifying a Config object. Within the scope, only values can be updated (new keys cannot be created). Upon

Squeeze dim only if it's not the last dim. Image dim expected to be *, H, W, C

obs_dict: must include "obs" key result: must include "action" key

Run before terminating to make sure all logs are flushed

Return numpy array as contiguous view of bytes if possible.

Dumps the config to a json. Args: filename (str): if not None, save to json file. Returns: json_str

Recursively apply functions to a nested dictionary or list or tuple, given a dictionary of {data_type: function_to_apply}. Args:

Recursively apply functions to a nested dictionary or list or tuple, given a dictionary of {data_type: function_to_apply}. Args:

Step in the environment with an action. Args: action (np.array): action to take Returns: observatio

Args: input_dim (int): dimension of inputs output_dim (int): dimension of outputs layer_dims ([int]): s

Helper function to register dataset link in global dictionary. Also takes a @horizon parameter - this corresponds to the evaluation rollo

Return length, i.e. Euclidean norm, of ndarray along axis. >>> v = numpy.random.random(3) >>> n = vector_norm(v) >>> numpy.allclose(n, nu

Returns a batch of samples from the prior distribution. Args: n (int): this argument is used to specify the number

Quick loading and saving for reserach, saves full state of the workspace. However, loading a snapshot assumes the code stays exactly

A full pass through the VAE network used during training to construct KL and reconstruction losses. See @VAE class for more info.

Creates an instance of a config from the algo name. Optionally pass a dictionary to instantiate the config from the dictionary.

Calling this function on this config indicates that key updates should be allowed even when this config is key-locked (but not when

A context scope for modifying a Config object. Within the scope, both keys and values can be updated. Upon leaving the scope,

Load to memory.

Return ndarray normalized by length, i.e. Euclidean norm, along axis. >>> v0 = numpy.random.random(3) >>> v1 = unit_vector(v0) >>> numpy.

Args: input_shape (tuple): shape of input (not including batch dimension) conv_kwargs (dict): kwargs for the conv1d b

Pass latents through decoder. Latents should be passed in to this function at train-time for backpropagation, but they can be