pg_reinforce.py 文件源码

def sampleAction(self, states):
    # TODO: use this code piece when tf.multinomial gets better
    # sample action from current policy
    # actions = self.session.run(self.predicted_actions, {self.states: states})[0]
    # return actions[0]

    # temporary workaround
    def softmax(y):
      """ simple helper function here that takes unnormalized logprobs """
      maxy = np.amax(y)
      e = np.exp(y - maxy)
      return e / np.sum(e)

    # epsilon-greedy exploration strategy
    if random.random() < self.exploration:
      return random.randint(0, self.num_actions-1)
    else:
      action_scores = self.session.run(self.action_scores, {self.states: states})[0]
      action_probs  = softmax(action_scores) - 1e-5
      action = np.argmax(np.random.multinomial(1, action_probs))
      return action