def newEpisode(self):
""" modify the original controller parameters and store the deltas """
DirectAgent.newEpisode(self)
if not self.evaluation:
self.deltaList.append(self.deltas.copy())
self.deltas = random.uniform(-self.epsilon, self.epsilon, len(self.controller.parameters))
self.controller.parameters = self.storedParameters + self.deltas
self.epsilon *= self.decay
def __init__(self, faClass=Linear):
self.deltas = None
self.alpha = 0.01
self.epsilon = 0.1
self.decay = 0.99
self.deltaList = []
self._evaluation = False
DirectAgent.__init__(self, faClass)
def forget(self):
DirectAgent.forget(self)
self.deltaList = []
def _setup(self, conditions):
""" setup the agent and copy the original parameters. """
DirectAgent._setup(self, conditions)
self.storedParameters = copy(self.controller.parameters)
self.deltas = random.uniform(-self.epsilon, self.epsilon, len(self.controller.parameters))