| Reinforcement learning: An introduction RS Sutton, AG Barto MIT press 1 (1), 9-11, 1998 | 90781 | 1998 |
| Policy gradient methods for reinforcement learning with function approximation RS Sutton, D McAllester, S Singh, Y Mansour Advances in neural information processing systems 12, 1999 | 10509 | 1999 |
| Learning to predict by the methods of temporal differences RS Sutton Machine learning 3 (1), 9-44, 1988 | 8941 | 1988 |
| Reinforcement learning: An Introduction, 1st edition RS Sutton, AG Barto MIT press, 1998 | 6375* | 1998 |
| Neuronlike adaptive elements that can solve difficult learning control problems AG Barto, RS Sutton, CW Anderson IEEE transactions on systems, man, and cybernetics 13 (5), 834-846, 1983 | 5570* | 1983 |
| Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning RS Sutton, D Precup, S Singh Artificial intelligence 112 (1-2), 181-211, 1999 | 5246 | 1999 |
| Integrated architectures for learning, planning, and reacting based on approximating dynamic programming RS Sutton Proceedings of the International Conference on Machine Learning, 216-224, 1990 | 2460 | 1990 |
| Generalization in reinforcement learning: Successful examples using sparse coarse coding RS Sutton Advances in neural information processing systems 8, 1995 | 1989 | 1995 |
| Toward a modern theory of adaptive networks: Expectation and prediction. RS Sutton, AG Barto Psychological review 88 (2), 135, 1981 | 1935 | 1981 |
| Neural networks for control WT Miller, PJ Werbos, RS Sutton MIT press, 1990 | 1855 | 1990 |
| Dyna, an integrated architecture for learning, planning, and reacting RS Sutton ACM Sigart Bulletin 2 (4), 160-163, 1991 | 1517 | 1991 |
| Temporal credit assignment in reinforcement learning RS Sutton University of Massachusetts, Amherst, http://www.incompleteideas.net/papers …, 1984 | 1388 | 1984 |
| Introduction to reinforcement learning, vol. 135 RS Sutton, AG Barto MIT press Cambridge 5, 21-22, 1998 | 1251 | 1998 |
| Eligibility traces for off-policy policy evaluation D Precup, RS Sutton, S Singh International Conference on Machine Learning 16, 759-766, 2000 | 1132 | 2000 |
| Reinforcement learning with replacing eligibility traces SP Singh, RS Sutton Machine learning 22 (1), 123-158, 1996 | 1126 | 1996 |
| Natural actor-critic algorithms S Bhatnagar, RS Sutton, M Ghavamzadeh, M Lee Automatica 7 (8), 12, 2009 | 1000 | 2009 |
| Reinforcement learning is direct adaptive optimal control RS Sutton, AG Barto, RJ Williams IEEE control systems magazine 12 (2), 19-22, 2002 | 904 | 2002 |
| Reward is enough D Silver, S Singh, D Precup, RS Sutton Artificial intelligence 299, 103535, 2021 | 889 | 2021 |
| Time-derivative models of Pavlovian reinforcement. RS Sutton, AG Barto Learning and Computational Neuroscience: Foundations of Adaptive Networks …, 1990 | 886 | 1990 |
| The bitter lesson, 2019 R Sutton URL http://www. incompleteideas. net/IncIdeas/BitterLesson. html, 2019 | 835* | 2019 |
Andrew BartoUniversity of Massachusetts AmherstVerified email at cs.umass.edu
