Loop-Avoidance Method for Load-Balancing Routing Algorithm

This paper introduces a method to reduce the occurrence of transfer loops on the network for the routing algorithm based on the reinforcement learning scheme 1n former study ， we proposed the routing algorithm “ DARLA" which fulfi11s the traffic shaping of the net-wor k. However ， our algorithm couldn't suppress the tra 伍 cusing the links toward the source of packets. This is due to the property of the characteristic of reinforce 司 ment learning. We show the method to estimate the lower bound of the probability for valid route for the destination ， and this lower bound can be used to reject the routes which cause the transfer loop