beta.py 文件源码

def tf_sample(self, distr_params, deterministic):
        alpha, beta, alpha_beta, _ = distr_params

        # Deterministic: mean as action
        definite = beta / alpha_beta

        # Non-deterministic: sample action using gamma distribution
        alpha_sample = tf.random_gamma(shape=(), alpha=alpha)
        beta_sample = tf.random_gamma(shape=(), alpha=beta)

        sampled = beta_sample / tf.maximum(x=(alpha_sample + beta_sample), y=util.epsilon)

        return self.min_value + (self.max_value - self.min_value) * \
            tf.where(condition=deterministic, x=definite, y=sampled)