Open AccessA Formal Verification Model for Performance Analysis of Reinforcement Learning Algorithms Applied to Dynamic Networks
Author(s) -
Shrirang Ambaji Kulkarni,
Raghavendra G . Rao
Publication year - 2017
Publication title -
journal of applied computer science and mathematics/journal of applied computer science
Language(s) - English
Resource type - Journals
eISSN - 2066-3129
pISSN - 1843-1046
DOI - 10.4316/jacsm.201701002
Subject(s) - reinforcement learning , computer science , artificial intelligence , algorithm , machine learning
Routing data packets in a dynamic network is a difficult and important problem in computer networks. As the network is dynamic, it is subject to frequent topology changes and is subject to variable link costs due to congestion and bandwidth. Existing shortest path algorithms fail to converge to better solutions under dynamic network conditions. Reinforcement learning algorithms posses better adaptation techniques in dynamic environments. In this paper we apply model based Q-Routing technique for routing in dynamic network. To analyze the correctness of Q-Routing algorithms mathematically, we provide a proof and also implement a SPIN based verification model. We also perform simulation based analysis of Q-Routing for given metrics