Type of Document	Master's Thesis
Author	Shiraev, Dmitry Eric
URN	etd-08242003-224906
Title	Inverse Reinforcement Learning and Routing Metric Discovery
Degree	Master of Science
Department	Computer Science
Advisory Committee	Advisor Name Title Ramakrishnan, Naren Committee Co-Chair Varadarajan, Srinidhi Committee Co-Chair Ribbens, Calvin J. Committee Member
Keywords	Inverse Reinforcement Learning Routing Network Metrics
Date of Defense	2003-08-22
Availability	unrestricted
Abstract Uncovering the metrics and procedures employed by an autonomous networking system is an important problem with applications in instrumentation, traffic engineering, and game-theoretic studies of multi-agent environments. This thesis presents a method for utilizing inverse reinforcement learning (IRL)techniques for the purpose of discovering a composite metric used by a dynamic routing algorithm on an Internet Protocol (IP) network. The network and routing algorithm are modeled as a reinforcement learning (RL) agent and a Markov decision process (MDP). The problem of routing metric discovery is then posed as a problem of recovering the reward function, given observed optimal behavior. We show that this approach is empirically suited for determining the relative contributions of factors that constitute a composite metric. Experimental results for many classes of randomly generated networks are presented.
Files	Filename       Size       Approximate Download Time (Hours:Minutes:Seconds)     28.8 Modem   56K Modem   ISDN (64 Kb)   ISDN (128 Kb)   Higher-speed Access    etd.pdf 235.01 Kb 00:01:05 00:00:33 00:00:29 00:00:14 00:00:01

If you have questions or technical problems, please Contact DLA.