main.py 文件源码

def obFixer(observation_space,observation): # fixes observation ranges, uses hyperbolic tangent for infinite values
  newObservation = []
  if observation_space.__class__ == gym.spaces.box.Box:
    for space in range(observation_space.shape[0]):
      high = observation_space.high[space]
      low = observation_space.low[space]
      if high == numpy.finfo(numpy.float32).max or high == float('Inf'):
        newObservation.append(math.tanh(observation[space]))
      else:
        dif = high - low 
        percent = (observation[space]+abs(low))/dif
        newObservation.append(((percent * 2)-1).tolist())
  if observation_space.__class__ == gym.spaces.discrete.Discrete:
    c = 0
    for neuron in range(observation_space.n):
      if observation == neuron:
        newObservation.append(1)
      else:
        newObservation.append(0)
  return newObservation