dqn_agent_nature.py 文件源码

def agent_start(self, observation):


        # Initialize State
        self.state = observation
        state_ = cuda.to_gpu(np.asanyarray(self.state, dtype=np.float32),self.gpu_id)

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

        # Update for next step
        self.lastAction = action
        self.last_state = self.state.copy()
        self.last_observation = observation.copy()
        self.max_Q_list.append(np.max(Q_now.get()))

        return action