KerasDDPGAgent.py 文件源码

def configure(self, observation_space_shape, nb_actions):
        # Next, we build a simple model.
        # actor network
        actor = Sequential()
        actor.add(Flatten(input_shape=(1,) + observation_space_shape))
        actor.add(Dense(16))
        actor.add(Activation('relu'))
        actor.add(Dense(16))
        actor.add(Activation('relu'))
        actor.add(Dense(16))
        actor.add(Activation('relu'))
        actor.add(Dense(nb_actions))
        actor.add(Activation('linear'))
        print(actor.summary())

        # critic network
        action_input = Input(shape=(nb_actions,), name='action_input')
        observation_input = Input(shape=(1,) + observation_space_shape, name='observation_input')
        flattened_observation = Flatten()(observation_input)
        x = concatenate([action_input, flattened_observation])
        x = Dense(32)(x)
        x = Activation('relu')(x)
        x = Dense(32)(x)
        x = Activation('relu')(x)
        x = Dense(32)(x)
        x = Activation('relu')(x)
        x = Dense(1)(x)
        x = Activation('linear')(x)
        critic = Model(input=[action_input, observation_input], output=x)
        print(critic.summary())

        # Finally, we configure and compile our agent. You can use every built-in Keras optimizer and
        # even the metrics!
        memory = SequentialMemory(limit=100000, window_length=1)
        random_process = OrnsteinUhlenbeckProcess(size=nb_actions, theta=.15, mu=0., sigma=.3)
        self.agent = DDPGAgent(nb_actions=nb_actions, actor=actor, critic=critic, critic_action_input=action_input,
                          memory=memory, nb_steps_warmup_critic=100, nb_steps_warmup_actor=100,
                          random_process=random_process, gamma=.99, target_model_update=1e-3)
        self.agent.compile(Adam(lr=.001, clipnorm=1.), metrics=['mae'])