Convert tensor to one-hot representation, assuming a certain number of total class labels. Args: tensor (torch.Tensor): tensor conta

Converts all numpy arrays in nested dictionary or list or tuple to torch tensors (and leaves existing torch Tensors as-is), and returns a

Adds dimension of size 1 at dimension @dim in all torch tensors and numpy arrays in nested dictionary or list or tuple and returns a new nest

Unsqueeze and expand a tensor at a dimension @dim by @size. Args: x (dict or list or tuple): a possibly nested dictionary or list or

Update any persistant state needed by guidance loss functions. - global_t : the current global timestep of rollout

stop_sign_pos: tensor [B, 2] stop_box_dim: tensor [B, 2]

Base function to execute a vectorization process. TODO: torch or np array input? Arguments: selected_track_id: selected_

guidance/constraint configs are for the given scene ONLY.

Compute yaws from position sequences. Optionally suppress yaws computed from low-velocity steps Args: pos (torch.Tensor): sequence o

Log probability of tensor x under a uniform mixture of Gaussians. Adapted from CS 236 at Stanford. Args: x (torch.Tensor): tensor

KL divergence loss between two discrete distributions. This function computes the average loss across the batch. Args: logp (torch.Te

Differs from parent by iterating on agents and not AV.

Args: train_config (TrainConfig): training config env_config (EnvConfig): environment config algo_config

Args: theta (np.ndarray): converging factor of the OU process sigma (np.ndarray): magnitude of the Gaussian noise add

- name : name of the guidance function (i.e. the type of guidance), must be in GUIDANCE_FUNC_MAP - weight : alpha weight, how much af

- buffer_len : additional space to leave between agents