sequence_decoder_actor_learner.py 文件源码

def choose_next_action(self, state):
        network_output_v, network_output_pi, action_repeat_probs = self.session.run(
            [
                self.local_network.output_layer_v,
                self.local_network.output_layer_pi,
                self.local_network.action_repeat_probs,
            ],
            feed_dict={
                self.local_network.input_ph: [state],
            })

        network_output_pi = network_output_pi.reshape(-1)
        network_output_v = np.asscalar(network_output_v)

        action_index = self.sample_policy_action(network_output_pi)
        new_action = np.zeros([self.num_actions])
        new_action[action_index] = 1

        action_repeat = 1 + self.sample_policy_action(action_repeat_probs[0])

        return new_action, network_output_v, network_output_pi, action_repeat