CV detail level: 0 10 [20/pdf/postscript/text] 30 40 50 60 70 80 90 100

Curriculum Vitae
Justin A. Boyan

Quick Jumps

  • Address
  • Summary
  • Projects/Systems
  • Chronology/Awards
  • Activities/Teaching
  • Refereed Publications
  • Unrefereed Publications
  • CV detail level: 0 10 [20/pdf/postscript/text] 30 40 50 60 70 80 90 100


    Massachusetts Institute of Technology
    Artificial Intelligence Lab
    545 Technology Square NE43-753
    Cambridge, MA 02139
    Phone: (617)-253-8005
    Fax: (617)-253-7781

    CV detail level: 0 10 [20/pdf/postscript/text] 30 40 50 60 70 80 90 100


    I am an applications-oriented machine learning researcher with strong mathematical skills, strong implementation skills, and significant entrepreneurial experience. My research focuses on creating efficient algorithms that use data to improve decision-making, with application to large-scale problems in optimization, control, scheduling, transportation planning, data mining and information retrieval.

    I am currently a Visiting Scientist at the MIT AI Lab, on assignment from my position as a research scientist at NASA Ames Research Center.

    CV detail level: 0 10 [20/pdf/postscript/text] 30 40 50 60 70 80 90 100

    Research Projects / Systems Developed

    2000- Adaptive Control of NASA Life Support Systems
    Developing learning-based controllers for life-support systems. These systems regulate the levels of air, water, food and energy for long-duration crew support in space. The associated control problems are dynamic, nonstationary, and safety-sensitive, requiring novel active-learning techniques. Work with Jeff Schneider, Leslie Kaelbling, and David Kortenkamp, in progress.
    2000 Internet Auction Trading Strategies
    Participated in the ICMAS-2000 Trading Agent Competition (TAC). This contest involved programming a travel agent to buy and sell airline tickets, hotel rooms, and entertainment tickets in 28 simultaneous Internet auctions, so as to construct profitable travel packages at minimum cost. Our entry included innovations in real-time resource allocation, pricing of single resources given combinatorial utilities, and risk mitigation. Work with Amy Greenwald.
    Results: winner (out of 25) in preliminary round; co-winner (out of 12) in finals.
    1999- Optimal Route Planning Under Time-Dependent Uncertainty
    Developed new representations and solutions for time-sensitive stochastic planning problems. Applications to telescope experiment scheduling and multimodal transportation planning. Work with Michael Littman and Mike Mitzenmacher, in progress. [2] [1]
    1996- Learning Evaluation Functions for Global Optimization
    Combined dynamic programming, function approximation and local search techniques into an algorithm that automatically constructs high-quality evaluation functions for fast combinatorial optimization. Applications to VLSI design, medical robotics, satisfiability, Bayes net structure-finding, geographic visualization, and information retrieval. Ph.D. thesis work. [14] [3] [15] [6] [8] [10]
    1994- Scaling Up Reinforcement Learning / Value Function Approximation
    Developed new algorithms for Value Function Approximation, solving large-scale high-dimensional control and scheduling problems with approximate dynamic programming. Work with Andrew Moore. [5] [7] [11] [12] [16]
    1996 Information Retrieval / Web Indexing / Machine Learning
    Developed LASER, a machine-learning-based search engine for the World Wide Web. Using non-intrusive feedback gathered from system users doing Web searches, it optimizes its retrieval function so as to provide better page rankings. Work with Dayne Freitag and Thorsten Joachims.
    1995-96 Anonymizing Proxy System for the World Wide Web
    Developed the Anonymizer, a custom proxy server that enables Web users to visit sites without revealing personal information such as their email address and Internet hostname. In April 1997, the system was sold to Infonex, Inc. and made available to the public at [9]
    1993-94 Reinforcement Learning for Network Routing / Multi-Agent Learning
    Invented Q-routing, a parallel distributed reinforcement-learning algorithm for routing packet traffic in a computer network. The routing tables adapt to varying network topologies and traffic loads. Work with Michael Littman. [13]
    1992-93 Artificial Neural Network algorithms
    Designed and tested extensions to cascading and modular neural network architectures. Work with Frank Fallside, Tony Robinson and Scott Fahlman.
    1992-94 Self-Learning Backgammon Software
    Wrote software combining temporal-difference learning and modular neural networks in order to train, from scratch, an expert-level computer backgammon player. My software now serves as the playing engine of MVP Backgammon, an award-winning commercial product.
    1986-95 Sole proprietor, BOYAN Communications
    Authored BOYAN Communications, a best-selling PC modem program. Maintained, documented, and marketed four major versions of the software over a ten-year life cycle.
    CV detail level: 0 10 [20/pdf/postscript/text] 30 40 50 60 70 80 90 100

    Chronology / Awards

    CV detail level: 0 10 [20/pdf/postscript/text] 30 40 50 60 70 80 90 100

    Professional Activities / Teaching

    2000-2003 Editorial Board, Machine Learning Journal
    1998 Invited speaker, Symposium on Applications of Reinforcement Learning, Stanford University
    I was one of fifteen invited speakers at this symposium.
    1996 Invited speaker, NSF Reinforcement Learning workshop, Harper's Ferry, WV
    I was one of three graduate students invited to participate in this national workshop.
    1995 Teaching Assistant, How to Think (Like a Computer Scientist)
    1993 Teaching Assistant, Artificial Neural Networks (graduate course)
    1992-1997 Organizer, CMU Reinforcement Learning Group
    1986-93 Mathematics teacher, Johns Hopkins University Center for Talented Youth residential summer program
    CV detail level: 0 10 [20/pdf/postscript/text] 30 40 50 60 70 80 90 100

    Selected Refereed Publications

    [1] [13 pages, gzipped postscript, 125K][13 pages, Adobe PDF, 246K] Boyan, J. A. and M. Mitzenmacher. "Improved Results for Route Planning in Stochastic Transportation Networks." Accepted to the 12th Annual Symposium on Discrete Algorithms (SODA), 2001.
    [2] [7 pages, gzipped postscript, 415K][7 pages, Adobe PDF, 194K] Boyan, J. A. and M. L. Littman. "Exact Solutions to Time-Dependent MDPs." To appear in Advances in Neural Information Processing Systems (NIPS). MIT Press, 2001.
    [3] [34 pages, gzipped postscript, 702K][34 pages, Adobe PDF, 592K] Boyan, J. A. and A. W. Moore. "Learning Evaluation Functions to Improve Local Search." Journal of Machine Learning Research, to appear, 2000.
    [4] [15 pages, gzipped postscript, 127K][15 pages, Adobe PDF, 353K] Boyan, J. A. "Technical Update: Least-Squares Temporal Difference Learning." Machine Learning Journal, to appear, 2000.
    [5] [8 pages, gzipped postscript, 80K][8 pages, Adobe PDF, 192K] Boyan, J. A. "Least-Squares Temporal Difference Learning." In Bratko, I., and Dzeroski, S., eds., Machine Learning: Proceedings of the Sixteenth International Conference (ICML), 1999.
    (Selected as ICML-99 Best Paper. One of 152 submissions received this honor.)
    [6] [ pages, gzipped postscript, 101K][ pages, Adobe PDF, 251K] Boyan, J. A. and A. W. Moore. "Learning Evaluation Functions for Global Optimization and Boolean Satisfiability." Fifteenth National Conference on Artificial Intelligence (AAAI), 1998.
    (Selected as an AAAI-98 Outstanding Paper. Three of 475 submissions received this honor.)
    [7] [ pages, gzipped postscript, 75K][ pages, Adobe PDF, 158K] Schneider, J. G., J. A. Boyan and A. W. Moore. "Value Function Based Production Scheduling." Machine Learning: Proceedings of the Fifteenth International Conference (ICML), 1998.
    [8] [17 pages, gzipped postscript, 486K][17 pages, Adobe PDF, 778K] Moore, A. W., J. G. Schneider, J. A. Boyan and M. S. Lee. "Q2: Memory-Based Active Learning for Optimizing Noisy Continuous Functions." Machine Learning: Proceedings of the Fifteenth International Conference (ICML), 1998.
    [9] [6 pages, gzipped postscript, 14K][6 pages, Adobe PDF, 20K] Boyan, J. A. "The Anonymizer: Protecting User Privacy on the Web." Computer-Mediated Communication Magazine, 4 (9), September 1997.
    [10] [12 pages, gzipped postscript, 103K][12 pages, Adobe PDF, 230K] Boyan, J. A. and A. W. Moore. "Using Prediction to Improve Combinatorial Optimization Search." Sixth International Workshop on Artificial Intelligence and Statistics (AISTATS), 1997.
    [11] [8 pages, gzipped postscript, 56K][8 pages, Adobe PDF, 206K] Boyan, J. A. and A. W. Moore. "Learning Evaluation Functions for Large Acyclic Domains." In L. Saitta (ed.), Machine Learning: Proceedings of the Thirteenth International Conference (ICML). Morgan Kaufmann, 1996.
    [12] [8 pages, gzipped postscript, 475K][8 pages, Adobe PDF, 769K] Boyan, J. A., and A. W. Moore, "Generalization in Reinforcement Learning: Safely Approximating the Value Function." In Tesauro, G., D. S. Touretzky, and T. K. Leen (eds.), Advances in Neural Information Processing Systems 7 (NIPS). MIT Press, 1995.
    [13] [8 pages, gzipped postscript, 37K][8 pages, Adobe PDF, 120K] Boyan, J. A., and M. L. Littman, "Packet routing in dynamically changing networks: A reinforcement learning approach." In Cowan, J. D., Tesauro, G., and Alspector, J. (eds.), Advances in Neural Information Processing Systems 6 (NIPS). Morgan Kaufmann, 1994.
    CV detail level: 0 10 [20/pdf/postscript/text] 30 40 50 60 70 80 90 100

    Selected Unrefereed Publications

    [14] [58 pages, gzipped postscript, 375K][58 pages, Adobe PDF, 1292K] Boyan, J. A. and W. L. Buntine, eds. "Statistical Machine Learning for Large-Scale Optimization." Neural Computing Surveys 3, 2000.
    [15] [216 pages, gzipped postscript, 619K][216 pages, Adobe PDF, 2831K] Boyan, J. A. "Learning Evaluation Functions for Global Optimization." Ph.D. thesis, Carnegie Mellon University, August 1998.
    [16] Boyan, J. A., A. W. Moore, and R. S. Sutton, Editors. "Proceedings of the Workshop on Value Function Approximation, Machine Learning Conference 1995." Carnegie Mellon Technical Report CMU-CS-95-206.
    CV detail level: 0 10 [20/pdf/postscript/text] 30 40 50 60 70 80 90 100
    Last modified: Mon Sep 25 2000