def _forwardImplementation(self, inbuf, outbuf):
""" Draws a random number between 0 and 1. If the number is less
than epsilon, a random action is chosen. If it is equal or
larger than epsilon, the greedy action is returned.
"""
assert self.module
values = self.module.getActionValues(self._state)
action = drawGibbs(values, self.tau)
self.tau *= self.decay
outbuf[:] = array([action])
def _legalizeIt(self, a):
""" draw index from an array of values, filtering out illegal moves. """
if not min(a) >= 0:
print(a)
print(min(a))
print(self.module.params)
print(self.module.inputbuffer)
print(self.module.outputbuffer)
raise Exception('Non-positive value in array?')
legals = self.game.getLegals(self.color)
vals = ones(len(a)) * (-100) * (1 + self.temperature)
for i in map(self._convertPosToIndex, legals):
vals[i] = a[i]
drawn = self._convertIndexToPos(drawGibbs(vals, self.temperature))
assert drawn in legals
return drawn