Returns a TimeStep with step_type set equal to StepType.FIRST.

Used in the notebooks

Used in the tutorials

observation A NumPy array, tensor, or a nested dict, list or tuple of arrays or tensors.
batch_size (Optional) A python or tensorflow integer scalar. If not provided, the environment will not be considered as a batched environment.
reward_spec If provided, the reward in the returned TimeStep will be compatible with the provided reward_spec.

A TimeStep.