@patent{bhya04,
  authors="Leemon C. Baird and Mance E. Harmon and R Reed. Young and James E. Armstrong",
  year="2004",
  title="US Patent #6,732,278:  Apparatus and method for authenticating access to a network resource",
  url="http://leemon.com/papers/index.html#bhya04"
}

@inproceedings{mbk99,
  authors="Andrew W. Moore and Leemon C. Baird and Leslie P. Kaelbling",
  year="1999",
  title="Multi-Value-Functions: Efficient Automatic Action Hierarchies for Multiple Goal MDPs",
  booktitle="Proceedings of the International Joint Conference on Artificial Intelligence",
  url="http://leemon.com/papers/index.html#mbk99"
}

@inproceedings{mbm99,
  authors="Remi . Munos and Leemon C. Baird and Andrew W. Moore",
  year="1999",
  title="Gradient Descent Approaches to Neural-Net-Based Solutions of the Hamilton-Jacobi-Bellman Equation",
  booktitle="Proceedings of the International Joint Conference on Neural Networks",
  url="http://leemon.com/papers/index.html#mbm99"
}

@inproceedings{bm99,
  authors="Leemon C. Baird and Andrew W. Moore",
  year="1999",
  title="Gradient descent for general reinforcement learning",
  booktitle="Advances in Neural Information Processing Systems 11",
  publisher="MIT Press",
  address="Cambridge, MA",
  editor=" M. S. Kearns, S. A. Solla, and D. A. Cohn, editors",
  url="http://leemon.com/papers/index.html#bm99"
}

@techreport{b99,
  authors="Leemon C. Baird",
  year="1999",
  title="Reinforcement Learning Through Gradient Descent",
  institution="Computer Science Department, Carnegie Mellon University",
  number="CMU-CS-99-132",
  note="PhD Thesis, Carnegie Mellon University, Pittsburgh, PA",
  url="http://leemon.com/papers/index.html#b99"
}

@article{wbp98,
  authors="Scott E. Weaver and Leemon C. Baird and Marios M. Polycarpou",
  year="1998",
  title="An Analytical Framework for Local Feedforward Networks",
  journal="IEEE Transactions on Neural Networks",
  volume="9",
  number="3",
  pages="473-482",
  note="Also published as Univeristy of Cincinnati Technical Report TR 195/07/96/ECECS",
  url="http://leemon.com/papers/index.html#wbp98"
}

@inproceedings{wbp98b,
  authors="Scott E. Weaver and Leemon C. Baird and Marios M. Polycarpou",
  year="1998",
  title="Preventing unlearning during on-line training of feedforward networks",
  booktitle="Proceedings of the International Symposium of Intelligent Control Gaithersburg, MD Sept 14-17",
  pages="359-364",
  url="http://leemon.com/papers/index.html#wbp98b"
}

@patent{b97,
  authors="Leemon C. Baird",
  year="1997",
  title="US Patent #5,608,843: Learning controller with advantage updating algorithm",
  url="http://leemon.com/papers/index.html#b97"
}

@article{bhk96,
  authors="Mance E. Harmon and Leemon C. Baird and A. Harry. Klopf",
  year="1996",
  title="Reinforcement Learning: An Alternative Approach to Machine Intelligence",
  journal="CrossTalk, The Journal of Defense Software Engineering",
  volume="9",
  number="2",
  pages="22-24",
  url="http://leemon.com/papers/index.html#bhk96"
}

@inproceedings{bvbhb96,
  authors="Ceaser . Bandera and F. J. Vico and J. M. Bravo and Mance E. Harmon and Leemon C. Baird",
  year="1996",
  title="Residual Q-learning applied to visual attention",
  booktitle="Proceedings of the Thirteenth International Conference on Machine Learning, Bari, Italy, 3-6 July",
  url="http://leemon.com/papers/index.html#bvbhb96"
}

@inproceedings{wbp96,
  authors="Scott E. Weaver and Leemon C. Baird and Marios M. Polycarpou",
  year="1996",
  title="An analytical framework for local feedforward networks",
  booktitle="International Symposium of Intelligent Control, Dearborn, MI, Sept 15-18",
  pages="450-455",
  url="http://leemon.com/papers/index.html#wbp96"
}

@inproceedings{wbp96b,
  authors="Scott E. Weaver and Leemon C. Baird and Marios M. Polycarpou",
  year="1996",
  title="Local feedforward networks",
  booktitle="Adaptive Distributive Parallel Computing, Dayton, OH, Aug 8-9",
  pages="280-290",
  url="http://leemon.com/papers/index.html#wbp96b"
}

@techreport{hb96,
  authors="Mance E. Harmon and Leemon C. Baird",
  year="1996",
  title="Spurious Solutions to the Bellman Equation",
  institution="Wright-Patterson Air Force Base Ohio: Wright Laboratory",
  number="WL-TR-96-'To Be Assigned'",
  note="Available from the Defense Technical Information Center, Cameron Station, Alexandria, VA 22304-6145",
  url="http://leemon.com/papers/index.html#hb96"
}

@techreport{hb96b,
  authors="Mance E. Harmon and Leemon C. Baird",
  year="1996",
  title="Metrics for Temporal Difference Learning",
  institution="Wright-Patterson Air Force Base Ohio: Wright Laboratory",
  number="WL-TR-96-1153",
  note="Available from the Defense Technical Information Center, Cameron Station, Alexandria, VA 22304-6145",
  url="http://leemon.com/papers/index.html#hb96b"
}

@techreport{hb96c,
  authors="Mance E. Harmon and Leemon C. Baird",
  year="1996",
  title="Multi-player residual advantage learning with general function approximation",
  institution="Wright-Patterson Air Force Base Ohio: Wright Laboratory",
  number="WL-TR-1065",
  note="Available from the Defense Technical Information Center, Cameron Station, Alexandria, VA 22304-6145",
  url="http://leemon.com/papers/index.html#hb96c"
}

@article{hbk95,
  authors="Mance E. Harmon and Leemon C. Baird and A. Harry. Klopf",
  year="1995",
  title="Reinforcement Learning Applied to a Differential Game",
  journal="Adaptive Behavior",
  publisher="MIT Press",
  volume="4",
  number="1",
  pages="3-28",
  url="http://leemon.com/papers/index.html#hbk95"
}

@inproceedings{b95,
  authors="Leemon C. Baird",
  year="1995",
  title="Residual Algorithms: Reinforcement Learning with Function Approximation",
  booktitle="Machine Learning: Proceedings of the Twelfth International Conference, 9-12 July, Morgan Kaufman Publishers, San Francisco, CA",
  editor="Armand Prieditis  and  Stuart Russell, editors",
  note="22 Nov 95 errata corrects errors in the published version",
  url="http://leemon.com/papers/index.html#b95"
}

@inproceedings{b95b,
  authors="Leemon C. Baird",
  year="1995",
  title="Residual Algorithms",
  booktitle="Proceedings of the Workshop on Value Function Approximation, Machine Learning Conference, July 9, (Technical report CMU-CS-95-206)",
  editor="Justin A. Boyan, Andrew W. Moore, Richard S. Sutton, editors",
  note="Workshop proceedings are at http://www.cs.cmu.edu/~reinf/ml95/proceedings.html",
  url="http://leemon.com/papers/index.html#b95b"
}

@inproceedings{hb95,
  authors="Mance E. Harmon and Leemon C. Baird",
  year="1995",
  title="Residual Advantage Learning Applied to a Differential Game",
  booktitle="Proceedings of the International Conference on Neural Networks, Washington D.C, 3-6 June",
  url="http://leemon.com/papers/index.html#hb95"
}

@inproceedings{wbp95,
  authors="Scott E. Weaver and Leemon C. Baird and Marios M. Polycarpou",
  year="1995",
  title="On the Localization of Feedforward Networks",
  booktitle="Proceedings of the American Control Conference",
  url="http://leemon.com/papers/index.html#wbp95"
}

@inproceedings{hbk95b,
  authors="Mance E. Harmon and Leemon C. Baird and A. Harry. Klopf",
  year="1995",
  title="Advantage Updating Applied to a Differential Game",
  booktitle="Advances in Neural Information Processing Systems 7",
  editor="Gerald Tesauro, et al, editors",
  publisher="MIT Press",
  address="Cambridge, MA",
  editor=" M. S. Kearns, S. A. Solla, and D. A. Cohn, editors",
  pages="353-360",
  publisher="MIT Press",
  url="http://leemon.com/papers/index.html#hbk95b"
}

@inproceedings{b94,
  authors="Leemon C. Baird",
  year="1994",
  title="Reinforcement Learning in Continuous Time: Advantage Updating",
  booktitle="Proceedings of the International Conference on Neural Networks, Orlando, FL, June",
  url="http://leemon.com/papers/index.html#b94"
}

@inproceedings{wb94,
  authors="Ron J. Williams and Leemon C. Baird",
  year="1994",
  title="Tight Performance Bounds on Greedy Policies Based on Imperfect Value Functions",
  booktitle="Proceedings of the Tenth Yale Workshop on Adaptive and Learning Systems, Yale University, June 1994",
  url="http://leemon.com/papers/index.html#wb94"
}

@techreport{b93,
  authors="Leemon C. Baird",
  year="1993",
  title="Advantage Updating",
  institution="Wright-Patterson Air Force Base Ohio: Wright Laboratory",
  number="WL-TR-93-1146",
  note="Available from the Defense Technical Information Center, Cameron Station, Alexandria, VA 22304-6145)",
  url="http://leemon.com/papers/index.html#b93"
}

@techreport{b93b,
  authors="Leemon C. Baird and A. Harry. Klopf",
  year="1993",
  title="Reinforcement Learning with High-Dimensional, Continuous Actions",
  institution="Wright-Patterson Air Force Base Ohio: Wright Laboratory",
  number="WL-TR-93-1147",
  note="Available from the Defense Technical Information Center, Cameron Station, Alexandria, VA 22304-6145",
  url="http://leemon.com/papers/index.html#b93b"
}

@techreport{wb93,
  authors="Ron J. Williams and Leemon C. Baird",
  year="1993",
  title="Analysis of Some Incremental Variants of Policy Iteration: First Steps Toward Understanding Actor-Critic Learning Systems",
  institution="Northeastern University",
  number="NU-CCS-93-11",
  month="Sep",
  url="http://leemon.com/papers/index.html#wb93"
}

@techreport{wb93b,
  authors="Ron J. Williams and Leemon C. Baird",
  year="1993",
  title="Tight Performance Bounds on Greedy Policies Based on Imperfect Value Functions",
  institution="Northeastern University",
  number="NU-CCS-93-14",
  month="Nov",
  url="http://leemon.com/papers/index.html#wb93b"
}

@inproceedings{b92,
  authors="Leemon C. Baird",
  year="1992",
  title="Function Minimization for Dynamic Programming Using Connectionist Networks",
  booktitle="Proceedings of the IEEE Conference On Systems, Man, and Cybernetics, Chicago, IL",
  pages="19-24",
  url="http://leemon.com/papers/index.html#b92"
}

@inproceedings{wb90,
  authors="Ron J. Williams and Leemon C. Baird",
  year="1990",
  title="A Mathematical Analysis of Actor-Critic Architectures for Learning Optimal Controls Through Incremental Dynamic Programming",
  booktitle="Proceedings of the Sixth Yale Workshop on Adaptive and Learning Systems, Yale University, 15-17 August",
  pages="96-101",
  url="http://leemon.com/papers/index.html#wb90"
}

@article{bw95,
  authors="Leemon C. Baird and P. S. P. Wang",
  year="1995",
  title="3-D object perception using gradient descent",
  journal="The Journal of Mathematical Imaging and Vision",
  volume="5",
  number="2",
  url="http://leemon.com/papers/index.html#bw95"
}

@article{bk94,
  authors="Leemon C. Baird and A. Harry. Klopf",
  year="1994",
  title="Reinforcement learning and optimal decision making",
  note="Invited book review of Rosenstein, G.,1991, Income and choice in biological control systems: A framework for understanding the function and dysfunction of the brain",
  journal="Journal of Mathematical Psychology",
  volume="38",
  number="3",
  publisher="Erlbaum",
  address="Hillsdale, NJ",
  url="http://leemon.com/papers/index.html#bk94"
}

@article{bk93,
  authors="Leemon C. Baird and A. Harry. Klopf",
  year="1993",
  title="A hierarchical network of provably optimal learning control systems: Extensions of the associative control process (ACP) network",
  journal="Adaptive Behavior",
  volume="1",
  number="3",
  pages="321-352",
  url="http://leemon.com/papers/index.html#bk93"
}

@inproceedings{bk93b,
  authors="Leemon C. Baird and A. Harry. Klopf",
  year="1993",
  title="Extensions of the associative control process (ACP) network: Hierarchies and provable optimality",
  booktitle="Proceedings of the Second International Conference on Simulation of Adaptive Behavior, Honolulu, Hawaii",
  url="http://leemon.com/papers/index.html#bk93b"
}

@techreport{babkmn93,
  authors="Walter L. Baker and S. C. Atkins and Leemon C. Baird and M. A. Koenig and Pete J. Millington and Noel F. Nistler",
  year="1993",
  title="Investigation of Drive-Reinforcement Learning and Application of Learning to Flight Control",
  institution="Charles Stark Draper Laboratory, Cambridge, MA",
  number="WL-TR-93-1153",
  url="http://leemon.com/papers/index.html#babkmn93"
}

@inproceedings{bw91,
  authors="Leemon C. Baird and P. S. P. Wang",
  year="1991",
  title="3D object recognition using gradient descent and the universal 3D ray grammar",
  booktitle="Proceedings of SPIE Conference on Intelligent Robots and Computer Vision X: Algorithms and Techniques, Boston, MA, vol. 1607",
  pages="711-719",
  url="http://leemon.com/papers/index.html#bw91"
}

@inproceedings{abbf91,
  authors="Jeff S. Alexander and Leemon C. Baird and Walter L. Baker and Jay A. Farrell",
  year="1991",
  title="A design  and  simulation tool for connectionist learning control systems: Application to autonomous underwater vehicles",
  booktitle="Proceedings of the Society for Computer Simulation Conference Baltimore, MD",
  url="http://leemon.com/papers/index.html#abbf91"
}

@techreport{b91,
  authors="Leemon C. Baird",
  year="1991",
  title="Learning and adaptive hybrid systems for nonlinear control",
  institution="Charles Stark Draper Laboratory, Cambridge, MA",
  number="CSDL-T-1099",
  note="Master's thesis, College of Computer Science, Northeastern University Boston",
  url="http://leemon.com/papers/index.html#b91"
}

@inproceedings{bb90,
  authors="Leemon C. Baird and Walter L. Baker",
  year="1990",
  title="A connectionist learning system for nonlinear control",
  booktitle="Proceedings of the AIAA Conference on Guidance, Navigation, and Control, Portland, Oregon",
  pages="1113-1119",
  url="http://leemon.com/papers/index.html#bb90"
}