def train(self):
networkFile = config.get('networkDir') + config.get(
'snapshotPrefix') + '_iter_' + config.get(
'trainingIterationsPerBatch') + '.caffemodel'
interactions = config.geti('trainInteractions')
minEpsilon = config.getf('minTrainingEpsilon')
epochSize = len(self.environment.imageList) / 1
epsilon = 1.0
self.controller.setEpsilonGreedy(epsilon,
self.environment.sampleAction)
epoch = 1
exEpochs = config.geti('explorationEpochs')
while epoch <= exEpochs:
s = cu.tic()
print 'Epoch', epoch, ': Exploration (epsilon=1.0)'
self.runEpoch(interactions, len(self.environment.imageList))
self.task.flushStats()
s = cu.toc('Epoch done in ', s)
epoch += 1
self.learner = QLearning()
self.agent.learner = self.learner
egEpochs = config.geti('epsilonGreedyEpochs')
while epoch <= egEpochs + exEpochs:
s = cu.tic()
epsilon = epsilon - (1.0 - minEpsilon) / float(egEpochs)
if epsilon < minEpsilon: epsilon = minEpsilon
self.controller.setEpsilonGreedy(epsilon,
self.environment.sampleAction)
print 'Epoch', epoch, '(epsilon-greedy:{:5.3f})'.format(epsilon)
self.runEpoch(interactions, epochSize)
self.task.flushStats()
self.doValidation(epoch)
s = cu.toc('Epoch done in ', s)
epoch += 1
maxEpochs = config.geti('exploitLearningEpochs') + exEpochs + egEpochs
while epoch <= maxEpochs:
s = cu.tic()
print 'Epoch', epoch, '(exploitation mode: epsilon={:5.3f})'.format(
epsilon)
self.runEpoch(interactions, epochSize)
self.task.flushStats()
self.doValidation(epoch)
s = cu.toc('Epoch done in ', s)
shutil.copy(networkFile, networkFile + '.' + str(epoch))
epoch += 1
def train(self):
networkFile = config.get('networkDir') + config.get('snapshotPrefix') + '_iter_' + config.get('trainingIterationsPerBatch') + '.caffemodel'
interactions = config.geti('trainInteractions')
minEpsilon = config.getf('minTrainingEpsilon')
epochSize = len(self.environment.imageList)/1
epsilon = 1.0
self.controller.setEpsilonGreedy(epsilon, self.environment.sampleAction)
epoch = 1
exEpochs = config.geti('explorationEpochs')
while epoch <= exEpochs:
s = cu.tic()
print 'Epoch',epoch,': Exploration (epsilon=1.0)'
self.runEpoch(interactions, len(self.environment.imageList))
self.task.flushStats()
s = cu.toc('Epoch done in ',s)
epoch += 1
self.learner = QLearning()
self.agent.learner = self.learner
egEpochs = config.geti('epsilonGreedyEpochs')
while epoch <= egEpochs + exEpochs:
s = cu.tic()
epsilon = epsilon - (1.0-minEpsilon)/float(egEpochs)
if epsilon < minEpsilon: epsilon = minEpsilon
self.controller.setEpsilonGreedy(epsilon, self.environment.sampleAction)
print 'Epoch',epoch ,'(epsilon-greedy:{:5.3f})'.format(epsilon)
self.runEpoch(interactions, epochSize)
self.task.flushStats()
self.doValidation(epoch)
s = cu.toc('Epoch done in ',s)
epoch += 1
maxEpochs = config.geti('exploitLearningEpochs') + exEpochs + egEpochs
while epoch <= maxEpochs:
s = cu.tic()
print 'Epoch',epoch,'(exploitation mode: epsilon={:5.3f})'.format(epsilon)
self.runEpoch(interactions, epochSize)
self.task.flushStats()
self.doValidation(epoch)
s = cu.toc('Epoch done in ',s)
shutil.copy(networkFile, networkFile + '.' + str(epoch))
epoch += 1
def runEpoch(self, interactions, maxImgs):
img = 0
s = cu.tic()
while img < maxImgs:
k = 0
while not self.environment.episodeDone and k < interactions:
self.experiment._oneInteraction()
k += 1
self.agent.learn()
self.agent.reset()
self.environment.loadNextEpisode()
img += 1
s = cu.toc('Run epoch with ' + str(maxImgs) + ' episodes', s)
def runEpoch(self, interactions, maxImgs):
img = 0
s = cu.tic()
while img < maxImgs:
k = 0
while not self.environment.episodeDone and k < interactions:
self.experiment._oneInteraction()
k += 1
self.agent.learn()
self.agent.reset()
self.environment.loadNextEpisode()
img += 1
s = cu.toc('Run epoch with ' + str(maxImgs) + ' episodes', s)
