Get all shapes of arrays and tensors in nested dictionary or list or tuple. Args: x (dict or list or tuple): a possibly nested dicti

Indexes all torch tensors and numpy arrays in dimension 1 with index @ind in nested dictionary or list or tuple and returns a new nested stru

Helper function to go from a list of flat dictionaries to a dictionary of lists. By "flat" we mean that none of the values are dictionaries,

Apply function @func to np.ndarray objects in a nested dictionary or list or tuple. Args: x (dict or list or tuple): a possibly

Apply function @tensor_func to torch.Tensor objects and @ndarray_func to np.ndarray objects in a nested dictionary or list or tuple. Ar

Reduces all tensors in nested dictionary or list or tuple at a dimension using a named reduction function. Args: x (dict or list

Pad a nested dictionary or list or tuple of sequence tensors in the time dimension (dimension 1). Args: seq (dict or list or tuple):

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

obs_dict: str: B,To,* return: B,Ta,Da

Repeat a dimension by combining expand and reshape operations. Args: x (dict or list or tuple): a possibly nested dictionary or list

Resets the environment using kwargs.

for grad-cam

for grad-cam

for grad-cam

actions: (n_action_steps,) + action_shape