| Theoretical models of learning to learn J Baxter Learning to learn, 71-94, 1998 | 2479* | 1998 |
| Boosting algorithms as gradient descent L Mason, J Baxter, PL Bartlett, MR Frean Advances in neural information processing systems 12 (NIPS 1999), 512-518, 2000 | 1586 | 2000 |
| A model of inductive bias learning J Baxter J. Artif. Intell. Res. (JAIR) 12, 149-198, 2000 | 1489 | 2000 |
| Infinite-horizon policy-gradient estimation J Baxter, PL Bartlett J. Artif. Intell. Res. (JAIR) 15, 319-350, 2001 | 1402* | 2001 |
| A Bayesian/information theoretic model of learning to learn via multiple task sampling J Baxter Machine learning 28, 7-39, 1997 | 648 | 1997 |
| Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning. E Greensmith, PL Bartlett, J Baxter Journal of Machine Learning Research 5 (9), 2004 | 633 | 2004 |
| Learning to play chess using temporal differences J Baxter, A Tridgell, L Weaver Machine Learning 40 (3), 243-263, 2000 | 408* | 2000 |
| Functional gradient techniques for combining hypotheses L Mason, J Baxter, PL Bartlett, M Frean Advances in Large-Margin Classifiers, 221-246, 2000 | 385 | 2000 |
| Learning Internal Representations (COLT 1995) J Baxter COLT '95: Proceedings of the eighth annual conference on Computational …, 1995 | 304* | 1995 |
| Improved generalization through explicit optimization of margins L Mason, PL Bartlett, J Baxter Machine Learning 38, 243-255, 2000 | 179 | 2000 |
| Reinforcement learning in POMDP's via direct gradient ascent J Baxter, PL Bartlett ICML '00 Proceedings of the Seventeenth International Conference on Machine …, 2000 | 152 | 2000 |
| Direct gradient-based reinforcement learning J Baxter, PL Bartlett Circuits and Systems, 2000. Proceedings. ISCAS 2000 Geneva. The 2000 IEEE …, 2000 | 139 | 2000 |
| Scaling internal-state policy-gradient methods for POMDPs D Aberdeen, J Baxter ICML '02 Proceedings of the Nineteenth International Conference on Machine …, 2002 | 113 | 2002 |
| A multi-agent, policy-gradient approach to network routing N Tao, J Baxter, L Weaver ICML '01 Proceedings of the Eighteenth International Conference on Machine …, 2001 | 98 | 2001 |
| The Evolution of Learning Algorithms for Artificial Neural Networks J Baxter Complex systems: From biology to computation, 313, 1993 | 81 | 1993 |
| Direct optimization of margins improves generalization in combined classifiers L Mason, PL Bartlett, J Baxter Advances in neural information processing systems 11 (NIPS 1998), 288-294, 1999 | 71 | 1999 |
| Experiments in parameter learning using temporal differences J Baxter, A Tridgell, L Weaver ICGA Journal 21 (2), 84-99, 1998 | 67 | 1998 |
| Machine learning system J Baxter US Patent 8,019,699, 2011 | 59 | 2011 |
| Estimation and approximation bounds for gradient-based reinforcement learning PL Bartlett, J Baxter Journal of Computer and System Sciences 64 (1), 133-150, 2002 | 57 | 2002 |
| 92¢/mflops/s, ultra-large-scale neural-network training on a piii cluster D Aberdeen, J Baxter, R Edwards SC'00: Proceedings of the 2000 ACM/IEEE Conference on Supercomputing, 44-44, 2000 | 47* | 2000 |
Peter BartlettProfessor, EECS and Statistics, UC BerkeleyVerified email at cs.berkeley.edu
