---
title: "Confidence Based Dual Reinforcement Q-Routing: An adaptive online network routing algorithm"
authors:
  - "Shailesh Kumar"
  - "Risto Miikkulainen"
doi: ""
url: "https://ijcai.org/proceedings/1999/108"
pdf: "https://ijcai.org/proceedings/1999/0108.pdf"
venue: "Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence"
year: 1999
pages: "758-762"
track: "Machine Learning"
keywords:
---

# Confidence Based Dual Reinforcement Q-Routing: An adaptive online network routing algorithm

Shailesh Kumar, Risto Miikkulainen

*Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence*, pages 758-762.

## Abstract

This paper describes and evaluates the Confidence-based Dual Reinforcement Q-Routing algorithm (CDRQ-Routing) for adaptive packet routing in communication networks. CDRQ-Routing is based on the Qlearning framework of Q-Routing. The main contribution of this work is the increased quantity and improved quality of exploration in CDRQ-Routing, which lead to faster adaptation and better routing policies learned as compared to Q-Routing, the state-of-the-art adaptive Bellman-Ford Routing, and the nonadaptive shortest path routing. Experiments over several network topologies have shown that at different loads, CDRQ-Routing learns superior policies significantly faster than QRouting. Moreover, CDRQ-Routing learns policies that sustain higher load levels than QRouting. Analysis shows that overhead due to exploration is insignificant as cqmpared to the improvements in CDRQ-Routing.