我试图在一个简单的异或函数上训练一个ActionValueNetwork
,但是结果看起来是随机的。在
""" Reinforcement Learning to learn xor function
"""
# generic import
import numpy as np
import random
# pybrain import
from pybrain.rl.explorers import EpsilonGreedyExplorer
from pybrain.rl.agents import LearningAgent
from pybrain.rl.learners.valuebased import ActionValueNetwork, NFQ
# The parameters of your algorithm
av_network = ActionValueNetwork(2, 2) # 2 dimensions in input, 2 actions possible (1 or 0)
learner = NFQ()
learner._setExplorer(EpsilonGreedyExplorer(0.0)) # No exploration
agent = LearningAgent(av_network, learner)
# The training
for _ in xrange(1,25): # we iterate 25 times
for x in xrange(1,4): # batch of 4 questions.
listxor = random.choice([[0, 0],[0, 1], [1, 0], [1, 1]])
resultxor = listxor[0]^listxor[1] # xor operation
agent.integrateObservation(listxor)
action = agent.getAction()
reward = 1 - 2*abs(resultxor - float(action[0])) # 1 if correct, -1 otherwise
print "xor(",listxor,") = ", resultxor, " || action = " , action[0], "reward = ", reward
agent.giveReward(reward)
agent.learn()
# Test
print "test : "
print "[0, 0] ", learner.module.getMaxAction([0, 0])
print "[0, 1] ", learner.module.getMaxAction([0, 1])
print "[1, 0] ", learner.module.getMaxAction([1, 0])
print "[1, 1] ", learner.module.getMaxAction([1, 1])
我知道,这不是Pybrain的定向方式(tast、env等),但我必须这样做。
我对ActionValueTable
和Q有很好的结果,但是我想使用每个维度的权重。在
有人能解释一下我哪里错了吗?网络好像什么也学不到。在
谢谢!在
目前没有回答
相关问题 更多 >
编程相关推荐