def step_async()

in level_replay/envs.py [0:0]

• 5 lines of code
• 4 McCabe index (conditional complexity)

    def step_async(self, actions):
        if isinstance(actions, torch.LongTensor) or len(actions.shape) > 1:
            # Squeeze the dimension for discrete actions
            actions = actions.squeeze(1)
        actions = actions.cpu().numpy()
        self.venv.step_async(actions)