Keras代码Q-learning OpenAI健身房FrozenLake出了点问题

Question

也许我的问题看起来很愚蠢。

我正在研究Q学习算法。为了更好地理解它，我尝试将this FrozenLake示例的Tenzorflow代码重新编译为Keras代码。

我的代码：

import gym
import numpy as np
import random

from keras.layers import Dense
from keras.models import Sequential
from keras import backend as K    

import matplotlib.pyplot as plt
%matplotlib inline

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

model = Sequential()
model.add(Dense(16, activation='relu', kernel_initializer='uniform', input_shape=(16,)))
model.add(Dense(4, activation='softmax', kernel_initializer='uniform'))

def custom_loss(yTrue, yPred):
    return K.sum(K.square(yTrue - yPred))

model.compile(loss=custom_loss, optimizer='sgd')

# Set learning parameters
y = .99
e = 0.1
#create lists to contain total rewards and steps per episode
jList = []
rList = []

num_episodes = 2000
for i in range(num_episodes):
    current_state = env.reset()
    rAll = 0
    d = False
    j = 0
    while j < 99:
        j+=1

        current_state_Q_values = model.predict(np.identity(16)[current_state:current_state+1], batch_size=1)
        action = np.reshape(np.argmax(current_state_Q_values), (1,))

        if np.random.rand(1) < e:
            action[0] = env.action_space.sample() #random action

        new_state, reward, d, _ = env.step(action[0])

        rAll += reward
        jList.append(j)
        rList.append(rAll)

        new_Qs = model.predict(np.identity(16)[new_state:new_state+1], batch_size=1)
        max_newQ = np.max(new_Qs)

        targetQ = current_state_Q_values
        targetQ[0,action[0]] = reward + y*max_newQ
        model.fit(np.identity(16)[current_state:current_state+1], targetQ, verbose=0, batch_size=1)
        current_state = new_state

        if d == True:
            #Reduce chance of random action as we train the model.
            e = 1./((i/50) + 10)
            break
print("Percent of succesful episodes: " + str(sum(rList)/num_episodes) + "%")

当我运行它时，它不能很好地工作：成功剧集的百分比：0.052％

plt.plot(rList)

original Tensorflow code更好：成功集数百分比：0.352％

plt.plot(rList)

我做错了什么？

Answer 1

除了在评论中提到的将use_bias = False设置为@Maldus之外，你可以尝试的另一件事是从更高的epsilon值开始（例如0.5,0.75）？一个技巧可能只是在达到目标时减少epsilon值。即每次剧集结束时不要减少epsilon。这样你的玩家可以随机地继续探索地图，直到它开始收敛于一条好的路线，然后减少epsilon参数是个好主意。

我实际上使用卷积层而不是密集层在此gist中在keras中实现了类似的模型。管理以使其在2000集以下的情况下工作。可能对别人有所帮助:)）