def sample_action()

in agents/bc_gan2.py [0:0]

• 6 lines of code
• 2 McCabe index (conditional complexity)

    def sample_action(self, state):
        if self.actor.training:
            self.actor.eval()
        state = torch.FloatTensor(state.reshape(1, -1)).to(self.device)
        action = self.actor.sample(state)
        return action.cpu().data.numpy().flatten()