Justin A. Boyan
Home * People * Justin A. Boyan
Justin Andrew Boyan,
an American computer scientist and product manager at Google. He holds a B.Sc. in mathematics from University of Chicago in 1991, a Master of Philosophy in computer speech and language processing from University of Cambridge in 1992 [2], and a Ph.D. in computer science from Carnegie Mellon University in 1998, where his advisors include Scott Fahlman and Andrew W. Moore [3] [4]. Until 2000, he was research scientist at NASA Ames Research Center with assignment as visiting scientist to MIT AI Lab. His research interests include artificial intelligence, statistical machine learning, information extraction, and optimization. In the early 90s, he wrote software combining temporal difference learning and modular neural networks in order to train an expert-level computer Backgammon player from scratch. His program Maestro placed second at the 4th Computer Olympiad, London 1992 [5].
Selected Publications
1990 ...
- Justin A. Boyan (1992). Modular Neural Networks for Learning Context-Dependent Game Strategies. Master's thesis, University of Cambridge, pdf
- Justin A. Boyan, Michael L. Littman (1993). Packet Routing in Dynamically Changing Networks: A Reinforcement Learning Approach. NIPS 1993, pdf
- Justin A. Boyan, Andrew W. Moore (1994). Generalization in Reinforcement Learning: Safely Approximating the Value Function. NIPS 1994, pdf
- Justin A. Boyan, Andrew W. Moore (1996). Learning Evaluation Functions for Large Acyclic Domains. ICML 1996, pdf
- Justin A. Boyan (1996). A Reinforcement Learning Framework for Combinatorial Optimization. AAAI/IAAI-96, Vol. 2, pdf
- Justin A. Boyan, Andrew W. Moore (1998). Learning Evaluation Functions for Global Optimization and Boolean Satisfiability. AAAAI/IAAI 1998, pdf
- Justin A. Boyan (1998). Least-Squares Temporal Difference Learning. Carnegie Mellon University, CMU-CS-98-152, pdf [8]
- Justin A. Boyan (1998). Learning Evaluation Functions for Global Optimization. Ph.D. thesis, Carnegie Mellon University, advisors Scott Fahlman and Andrew W. Moore, zipped ps
2000 ...
- Justin A. Boyan (2002). Technical Update: Least-Squares Temporal Difference Learning. Machine Learning, Vol. 49, pdf
- Amy Greenwald, Justin A. Boyan (2004, 2012). Bidding under Uncertainty: Theory and Experiments. UAI 2004, arXiv:1207.4108
External Links
- Justin Boyan | LinkedIn
- Curriculum Vitae - Justin Andrew Boyan
- Justin Boyan - Google+
- Justin Boyan (@jboyan) | Twitter
- Justin Boyan's ICGA Tournaments
- Justin Boyan - The Mathematics Genealogy Project
References
- ↑ Justin Boyan | LinkedIn
- ↑ Justin A. Boyan (1992). Modular Neural Networks for Learning Context-Dependent Game Strategies. Master's thesis, University of Cambridge, pdf
- ↑ Justin Boyan - The Mathematics Genealogy Project
- ↑ Justin A. Boyan (1998). Learning Evaluation Functions for Global Optimization. Ph.D. thesis, Carnegie Mellon University, advisors Scott Fahlman and Andrew W. Moore
- ↑ Curriculum Vitae - Justin Andrew Boyan
- ↑ dblp: Justin A. Boyan
- ↑ Curriculum Vitae - Justin Andrew Boyan
- ↑ ICML-99 Best Paper Award
