def useAgent(symbol, timeframe, terminal, dataUpdater, dataManager,
hkFeatList, saveDir, genPath, agentName, timeConstraint):
###############################
# use agent on test
###############################
useCpu(nThreads=8, nCores=8)
openerPriceDiffGenerator = MultiScalerDiffGenerator(featureList=hkFeatList).loadGenerator(genPath)
buyerPriceDiffGenerator = MultiScalerDiffGenerator(featureList=hkFeatList).loadGenerator(genPath)
sellerPriceDiffGenerator = MultiScalerDiffGenerator(featureList=hkFeatList).loadGenerator(genPath)
openerPriceDiffGenerator.setFitMode(False)
buyerPriceDiffGenerator.setFitMode(False)
sellerPriceDiffGenerator.setFitMode(False)
testEnv = RealCompositeEnv(symbol, timeframe, terminal, dataUpdater, dataManager,
openerPriceDiffGenerator, buyerPriceDiffGenerator, sellerPriceDiffGenerator,
startDeposit=300, lotSize=0.1, lotCoef=100000, stopType="adaptive", takeType="adaptive",
stoplossPuncts=100, takeprofitPuncts=200, stopPos=2, takePos=1, maxLoss=40000,
maxTake=40000, riskPoints=110, riskLevels=5, renderFlag=False)
# get size of state and action from environment
openerAgent = DQNAgent(testEnv.observation_space["opener"], testEnv.action_space["opener"].n)
buyerAgent = DQNAgent(testEnv.observation_space["buyer"], testEnv.action_space["buyer"].n)
sellerAgent = DQNAgent(testEnv.observation_space["seller"], testEnv.action_space["seller"].n)
agent = CompositeAgent(openerAgent, buyerAgent, sellerAgent)
agent = agent.load_agent(saveDir, agentName, dropSupportModel=True)
# agent = agent.load_agent("./", "checkpoint_composite")
print("start using agent")
startTime = datetime.now()
agent.use_agent(testEnv, timeConstraint=timeConstraint)
endTime = datetime.now()
print("Use time: {}".format(endTime - startTime))
reset_keras()
startDeposit=300, lotSize=0.1, lotCoef=100000, spread=18, spreadCoef=0.00001,
stopType="adaptive", takeType="adaptive", stopPos=1, takePos=1, maxLoss=20000, maxTake=20000,
stoplossPuncts=20000, takeprofitPuncts=20000, riskPoints=110, riskLevels=5, parallelOpener=False,
renderDir="../models/", renderName="back_plot")
# get size of state and action from environment
openerAgent = DQNAgent(trainEnv.observation_space["opener"], trainEnv.action_space["opener"].n,
memorySize=40000, batch_size=20, train_start=20000, epsilon_min=0.2, epsilon=1, discount_factor=0.99,
epsilon_decay=0.9999, learning_rate=0.0001)
buyerAgent = DQNAgent(trainEnv.observation_space["buyer"], trainEnv.action_space["buyer"].n,
memorySize=40000, batch_size=20, train_start=10000, epsilon_min=0.2, epsilon=1, discount_factor=0.99,
epsilon_decay=0.9999, learning_rate=0.0001)
sellerAgent = DQNAgent(trainEnv.observation_space["seller"], trainEnv.action_space["seller"].n,
memorySize=40000, batch_size=20, train_start=10000, epsilon_min=0.2, epsilon=1, discount_factor=0.99,
epsilon_decay=0.9999, learning_rate=0.0001)
agent = CompositeAgent(openerAgent, buyerAgent, sellerAgent)
###################################
#agent = agent.load_agent("../models/", "best_composite")
#agent.agents["opener"].epsilon_min = 0.1
#agent.agents["buy"].epsilon_min = 0.1
#agent.agents["sell"].epsilon_min = 0.1
#agent = agent.load_agent("../models/", "checkpoint_composite")
###################################
lastSaveEp = agent.fit_agent(env=trainEnv, backTestEnv=backTestEnv, nEpisodes=30, nWarmUp=0,
uniformEps=False, synEps=False, plotScores=False,
saveBest=True, saveFreq=1, saveDir="../models/", saveName="best_composite")
endTime = datetime.now()
print("Training finished. Total time: {}".format(endTime - startTime))
###############################
parallelOpener=False,
renderDir="../models/",
renderName="test_plot")
# get size of state and action from environment
flattener = FeatureFlattener().loadFlattener(
"../models/", "flattener_{}_{}".format(symbol, timeframe))
modelsPack = load("../models/classic_models_pack.pkl")
openerAgent = FlatModelsAverager(flattener, modelsPack)
buyerAgent = AlwaysHoldAgent(testEnv.observation_space["opener"],
testEnv.action_space["opener"].n,
agentName="buyer")
sellerAgent = AlwaysHoldAgent(testEnv.observation_space["seller"],
testEnv.action_space["seller"].n,
agentName="seller")
agent = CompositeAgent(openerAgent, buyerAgent, sellerAgent)
print("start using agent")
dealsStatistics = agent.use_agent(testEnv)
###########################
import numpy as np
dealAvg = np.sum(dealsStatistics) / len(dealsStatistics)
dealStd = np.std(dealsStatistics)
print("Avg deal profit: {}".format(dealAvg))
print("Deal's std: {}".format(dealStd))
###########################
sumRew = 0
cumulativeReward = []
for i in range(len(dealsStatistics)):
sumRew += dealsStatistics[i]
renderDir="../models/",
renderName="test_plot")
# get size of state and action from environment
openerAgent = DQNAgent(testEnv.observation_space["opener"],
testEnv.action_space["opener"].n,
fillMemoryByPretrainedModel=True)
buyerAgent = DQNAgent(testEnv.observation_space["buyer"],
testEnv.action_space["buyer"].n,
fillMemoryByPretrainedModel=True)
sellerAgent = DQNAgent(testEnv.observation_space["seller"],
testEnv.action_space["seller"].n,
fillMemoryByPretrainedModel=True)
#buyerAgent = AlwaysHoldAgent(testEnv.observation_space["opener"], testEnv.action_space["opener"].n, agentName="buyer")
#sellerAgent = AlwaysHoldAgent(testEnv.observation_space["seller"], testEnv.action_space["seller"].n, agentName="seller")
agent = CompositeAgent(openerAgent, buyerAgent, sellerAgent)
#agent = agent.load_agent("../models/", "best_composite", dropSupportModel=True)
#agent = agent.loadPretrainedAgents(dir="../models/", baseName="super_resnet_34_{}_{}".format(symbol, timeframe))
agent = agent.loadPretrainedAgents(dir="../models/", baseName="qrl_resnet_34")
#agent = agent.load_agent("../models/", "checkpoint_composite")
print("start using agent")
dealsStatistics = agent.use_agent(testEnv)
###########################
import numpy as np
dealAvg = np.sum(dealsStatistics) / len(dealsStatistics)
dealStd = np.std(dealsStatistics)
print("Avg deal profit: {}".format(dealAvg))
print("Deal's std: {}".format(dealStd))
###########################
renderDir="../models/",
renderName="test_plot")
# get size of state and action from environment
openerAgent = DQNAgent(testEnv.observation_space["opener"],
testEnv.action_space["opener"].n,
fillMemoryByPretrainedModel=True)
#buyerAgent = DQNAgent(testEnv.observation_space["buyer"], testEnv.action_space["buyer"].n, fillMemoryByPretrainedModel=True)
#sellerAgent = DQNAgent(testEnv.observation_space["seller"], testEnv.action_space["seller"].n, fillMemoryByPretrainedModel=True)
buyerAgent = AlwaysHoldAgent(testEnv.observation_space["opener"],
testEnv.action_space["opener"].n,
agentName="buyer")
sellerAgent = AlwaysHoldAgent(testEnv.observation_space["seller"],
testEnv.action_space["seller"].n,
agentName="seller")
agent = CompositeAgent(openerAgent, buyerAgent, sellerAgent)
#agent = agent.load_agent("../models/", "best_composite", dropSupportModel=True)
agent = agent.loadPretrainedAgents(dir="../models/",
baseName="super_resnet_34_{}_{}".format(
symbol, timeframe))
#agent = agent.loadPretrainedAgents(dir="../models/", baseName="qrl_resnet_34")
#agent = agent.load_agent("../models/", "checkpoint_composite")
print("start using agent")
dealsStatistics = agent.use_agent(testEnv)
###########################
import numpy as np
dealAvg = np.sum(dealsStatistics) / len(dealsStatistics)
dealStd = np.std(dealsStatistics)