Keras 代码有问题 Q-learning OpenAI 健身房 FrozenLake

也许我的问题会显得很愚蠢。

我正在研究 Q-learning 算法。为了更好地理解它，我正在尝试重新制作 Tenzorflow 代码这个结冰的湖 https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-0-q-learning-with-tables-and-neural-networks-d195264329d0将示例写入 Keras 代码中。

My code:

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，它效果不佳：成功剧集百分比：0.052%

plt.plot(rList)

The 原始张量流代码 https://medium.com/emergent-future/simple-reinforcement-learning-with-tensorflow-part-0-q-learning-with-tables-and-neural-networks-d195264329d0好多了：成功剧集百分比：0.352%

plt.plot(rList)

我做错了什么？

除了像评论中提到的 @Maldus 设置 use_bias=False 之外，您可以尝试的另一件事是从更高的 epsilon 值开始（例如 0.5、0.75）？一个技巧可能是仅在达到目标时才降低 epsilon 值。即不要在每集结束时减少 epsilon。这样你的玩家就可以继续随机探索地图，直到它开始收敛在一条好的路线上，然后减少 epsilon 参数将是一个好主意。

我实际上在 keras 中实现了类似的模型gist https://gist.github.com/weiji14/bab587907681869ec0f70f7496f98a12使用卷积层而不是密集层。设法让它在 2000 集以内运行。可能对其他人有一些帮助:)