函数逼近和q-learning

时间:2017-08-25 17:07:53

标签: reinforcement-learning openai-gym

我正在尝试使用动作值近似函数实现q学习。我正在使用openai-gym和“MountainCar-v0”环境来测试我的算法。我的问题是,它根本没有收敛或找到目标。

基本上,逼近器的工作原理如下,您可以输入2个特征:位置和速度以及单热编码中的3个动作之一:0 - > [1,0,0],1 - > [0,1,0]和2 - > [0,0,1]。对于一个特定动作,输出是动作值近似值Q_approx(s,a)。

我知道通常,输入是状态(2个特征),输出层包含每个动作的1个输出。我看到的最大区别是我已经运行前馈传递3次(每个操作一次)并获取最大值,而在标准实现中,您运行一次并在输出上取最大值。

也许我的实施完全错误,我想错了。要在这里粘贴代码,这是一团糟,但我只是尝试了一下:

import gym
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Activation

env = gym.make('MountainCar-v0')

# The mean reward over 20 episodes
mean_rewards = np.zeros(20)
# Feature numpy holder
features = np.zeros(5)
# Q_a value holder
qa_vals = np.zeros(3)

one_hot = {
    0 : np.asarray([1,0,0]),
    1 : np.asarray([0,1,0]),
    2 : np.asarray([0,0,1])
}

model = Sequential()
model.add(Dense(20, activation="relu",input_dim=(5)))
model.add(Dense(10,activation="relu"))
model.add(Dense(1))
model.compile(optimizer='rmsprop',
              loss='mse',
              metrics=['accuracy'])

epsilon_greedy = 0.1
discount = 0.9
batch_size = 16

# Experience replay containing features and target 
experience = np.ones((10*300,5+1))

# Ring buffer
def add_exp(features,target,index):
    if index % experience.shape[0] == 0:
        index = 0
        global filled_once
        filled_once = True
    experience[index,0:5] = features
    experience[index,5] = target
    index += 1
    return index

for e in range(0,100000):
    obs = env.reset()
    old_obs = None
    new_obs = obs
    rewards = 0
    loss = 0
    for i in range(0,300):

        if old_obs is not None:
            # Find q_a max for s_(t+1)
            features[0:2] = new_obs
            for i,pa in enumerate([0,1,2]):
                features[2:5] = one_hot[pa]
                qa_vals[i] = model.predict(features.reshape(-1,5))

            rewards += reward
            target = reward + discount*np.max(qa_vals) 

            features[0:2] = old_obs
            features[2:5] = one_hot[a]

            fill_index = add_exp(features,target,fill_index)

            # Find new action
            if np.random.random() < epsilon_greedy:
                a = env.action_space.sample()
            else:
                a = np.argmax(qa_vals)
        else:
            a = env.action_space.sample()

        obs, reward, done, info = env.step(a)

        old_obs = new_obs
        new_obs = obs

        if done:
            break

        if filled_once:
            samples_ids = np.random.choice(experience.shape[0],batch_size)
            loss += model.train_on_batch(experience[samples_ids,0:5],experience[samples_ids,5].reshape(-1))[0]
    mean_rewards[e%20] = rewards
    print("e = {} and loss = {}".format(e,loss))
    if e % 50 == 0:
        print("e = {} and mean = {}".format(e,mean_rewards.mean()))

提前致谢!

1 个答案:

答案 0 :(得分:1)

作为网络输入的操作或网络的不同输出之间应该没有太大区别。如果您的状态是图像,它确实会产生巨大的差异。因为Conv网在图像上运行良好,并且没有明显的方法将动作集成到输入中。

您是否尝试过cartpole平衡环境?最好测试您的模型是否正常工作。

爬山很难。在你达到顶峰之前它没有奖励,这通常根本不会发生。一旦你到达顶部,模型将只开始学习一些有用的东西。如果你永远不会达到顶峰,你应该增加你的探索时间。换句话说,采取更多随机行动,更多......