def __init__(self, net, task, valueNetwork=None, **args):
self.net = net
self.task = task
self.setArgs(**args)
if self.valueLearningRate == None:
self.valueLearningRate = self.learningRate
if self.valueMomentum == None:
self.valueMomentum = self.momentum
if self.supervisedPlotting:
from pylab import ion
ion()
# adaptive temperature:
self.tau = 1.
# prepare the datasets to be used
self.weightedDs = ImportanceDataSet(self.task.outdim, self.task.indim)
self.rawDs = ReinforcementDataSet(self.task.outdim, self.task.indim)
self.valueDs = SequentialDataSet(self.task.outdim, 1)
# prepare the supervised trainers
self.bp = BackpropTrainer(self.net, self.weightedDs, self.learningRate,
self.momentum, verbose=False,
batchlearning=True)
# CHECKME: outsource
self.vnet = valueNetwork
if valueNetwork != None:
self.vbp = BackpropTrainer(self.vnet, self.valueDs, self.valueLearningRate,
self.valueMomentum, verbose=self.verbose)
# keep information:
self.totalSteps = 0
self.totalEpisodes = 0
def __init__(self, indim, outdim):
# store input and output dimension
self.indim = indim
self.outdim = outdim
# create the history dataset
self.history = ReinforcementDataSet(indim, outdim)
def __init__(self, indim, outdim):
# store input and output dimension
self.indim = indim
self.outdim = outdim
# create history dataset
self.remember = True
self.history = ReinforcementDataSet(indim, outdim)
# initialize temporary variables
self.lastobs = None
self.lastaction = None
def __init__(self, ):
Q.__init__(self, const.ALPHA, const.GAMMA)
self.explorer = FeasibleEpsilonGreedyExplorer(const.EPSILON, const.DECAY)
self.dataset2 = ReinforcementDataSet(1, 1)
