def testQValueNetwork(startTurn=0, loopNum=1000, type=''):
agents = []
win_nums = {}
test_name = PLAYER_LIST[type][0]
test_filename = TEST[type]
if os.path.isfile(test_filename):
with open(test_filename, 'r') as f:
win_nums = pickle.load(f)
for i in range(0, 3):
playerName = PLAYER_LIST[type][i]
nw = NETWORK[type](playerName)
if playerName == test_name:
nw.loadNet(playerName, startTurn)
rfa = AGENT[type](playerName, nw)
agents.append(rfa)
env = RunFastEnvironment()
exp = Experiment(env, agents)
for i in range(loopNum):
if not win_nums.get(startTurn):
win_nums[startTurn] = {}
testHistory = exp.doTest(test_name)
for j in range(0,3):
playerName = PLAYER_LIST[type][j]
if not win_nums[startTurn].get(playerName):
win_nums[startTurn][playerName] = {'point': 0, 'win': 0}
win_nums[startTurn][playerName]['point'] += testHistory[playerName]
if testHistory['name'] == playerName:
win_nums[startTurn][playerName]['win'] += 1
with open(test_filename, 'w') as f:
pickle.dump(win_nums, f)
def testQValueNetwork(startTurn=0, loopNum=1000, testName='player0', filename='test_winners_nn', playerNamePrefix='player', type=1, inputNum=192):
'''
在测试时，其他的两个agent都不选用最佳的network，只有测试对象使用
然后测试对象每次选取最佳的行动，其他的两个agent有50%概率选择最佳行动，不过他们的net应该是最普通的，没有经过训练的
winNums = {trainNum: {player0: {'point': xxx, 'win': yyy}, player1: {...}}}
'''
agents = []
winNums = {}
if os.path.isfile(filename):
with open(filename, 'r') as f:
winNums = pickle.load(f)
print 'loading agents'
for i in range(0, 3):
playerName = PLAYER_LIST[i]
nw = RunFastNetwork(playerName, inputNum=inputNum, hiddenNum=inputNum, outNum=1)
if playerName == testName:
nw.loadNet(testName, startTurn)
rfa = RunFastAgent(playerName, nw)
agents.append(rfa)
env = RunFastEnvironment()
exp = Experiment(env, agents, type=type)
print 'set up the experiment'
for i in range(startTurn, startTurn + loopNum):
if not winNums.get(startTurn):
winNums[startTurn] = {}
testHistory = exp.doTest(testName)
for j in range(0,3):
playerName = PLAYER_LIST[j]
if not winNums[startTurn].get(playerName):
winNums[startTurn][playerName] = {'point': 0, 'win': 0}
winNums[startTurn][playerName]['point'] += testHistory[playerName]
if testHistory['name'] == playerName:
winNums[startTurn][playerName]['win'] += 1
print str(i-startTurn), winNums
print winNums
with open(filename, 'w') as f:
pickle.dump(winNums, f)
def testQValueNetwork(startTurn=0, loopNum=1000, testName='player0', filename='win_nums', type=1, inputNum=192):
agents = []
winNums = {}
if os.path.isfile(filename):
with open(filename, 'r') as f:
winNums = pickle.load(f)
print 'loading agents'
for i in range(0, 3):
playerName = PLAYER_LIST[i]
nw = RunFastDeepNetwork(playerName, inputNum=inputNum, hidden1Num=inputNum, hidden2Num=inputNum, hidden3Num=inputNum, outNum=1)
if playerName == testName:
nw.loadNet(playerName, startTurn)
rfa = RunFastAgent(playerName, nw)
agents.append(rfa)
env = RunFastEnvironment()
exp = Experiment(env, agents, type=type)
print 'set up the experiment'
for i in range(startTurn, startTurn + loopNum):
if not winNums.get(startTurn):
winNums[startTurn] = {}
testHistory = exp.doTest(testName)
for j in range(0,3):
playerName = PLAYER_LIST[j]
if not winNums[startTurn].get(playerName):
winNums[startTurn][playerName] = {'point': 0, 'win': 0}
winNums[startTurn][playerName]['point'] += testHistory[playerName]
if testHistory['name'] == playerName:
winNums[startTurn][playerName]['win'] += 1
print str(i-startTurn), winNums
print winNums
with open(filename, 'w') as f:
pickle.dump(winNums, f)
