predictron.py 文件源码

def lambda_preturn_network(preturns, lambdas):
  # Final lamdba must be zero
  final_lambda = tf.Assert(
      tf.reduce_all(tf.equal(lambdas[:, -1, :], 0.0)), [lambdas[:, -1, :]])

  with tf.control_dependencies([final_lambda]):
    with tf.variable_scope('lambda_preturn'):
      accum_lambda = tf.cumprod(lambdas, axis=1, exclusive=True)
      lambda_bar = (1 - lambdas) * accum_lambda  # This should always sum to 1
      lambda_preturn = tf.reduce_sum(
          lambda_bar * preturns, reduction_indices=1)

      util.activation_summary(lambda_preturn)
      return lambda_preturn