a3C.py 文件源码

def actor_loss(self):
        if self.config.mode == 'discrete':
            log_prob = tf.reduce_sum(tf.log(self.a_prob) * tf.one_hot(self.action_input, self.action_dim, dtype=tf.float32),
                                     axis=1, keep_dims=True)
            # use entropy to encourage exploration
            exp_v = log_prob * self.TD_loss
            entropy = -tf.reduce_sum(self.a_prob * tf.log(self.a_prob), axis=1, keep_dims=True)  # encourage exploration
            exp_v = self.config.ENTROPY_BETA * entropy + exp_v
            return tf.reduce_mean(-exp_v)  # ????????log_prb????????????????????TD_loss
        elif self.config.mode == 'continuous':
            log_prob = self.action_normal_dist.log_prob(self.action_input)
            exp_v = log_prob * self.TD_loss
            # use entropy to encourage exploration
            exp_v = self.config.ENTROPY_BETA * self.action_normal_dist.entropy() + exp_v
            return tf.reduce_mean(-exp_v)