dqn.py 文件源码

def start(self,x=None):
        if x is None:
            x=Tensor.context


        obs_array = x.content.data
        #print "sum",obs_array.sum()

        # Initialize State
        self.state = np.zeros((self.func.hist_size, self.image_feature_dim), dtype=np.uint8)
        self.state[0] = obs_array
        state_ = np.asanyarray(self.state.reshape(1, self.func.hist_size, self.image_feature_dim), dtype=np.float32)
        if Deel.gpu >= 0:
            state_ = cuda.to_gpu(state_)

        # Generate an Action e-greedy
        action, Q_now = self.func.e_greedy(state_, self.epsilon)
        returnAction = action

        # Update for next step
        self.lastAction = copy.deepcopy(returnAction)
        self.last_state = self.state.copy()
        self.last_observation = obs_array

        return returnAction