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

我正在研究Q学习算法.为了更好地理解它,我试图将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,效果不佳：成功集数的百分比：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？