Philip Thomas

Cited by

	All	Since 2017
Citations	2751	2355
h-index	25	24
i10-index	45	42

680

340

170

510

20102011201220132014201520162017201820192020202120227 16 26 28 40 71 135 178 255 421 572 679 249

Public access

View all

21 articles

0 articles

available

not available

Based on funding mandates

Co-authors

Georgios TheocharousAdobe ResearchVerified email at adobe.com
Emma BrunskillAssociate Professor of Computer Science, Stanford UniversityVerified email at cs.stanford.edu
Yash ChandakPhD Candidate, University of Massachusetts, AmherstVerified email at cs.umass.edu
Bruno Castro da SilvaUniversity of MassachusettsVerified email at cs.umass.edu
Antonie J. (Ton) van den BogertProfessor of Mechanical Engineering, Cleveland State UniversityVerified email at csuohio.edu
Scott M. JordanPhD Candidate, University of Massachusetts AmherstVerified email at cs.umass.edu
George KonidarisBrownVerified email at cs.brown.edu
Michael BranickyProfessor of Electrical Engineering & Computer Science, University of KansasVerified email at ku.edu
Stephen GiguereUniversity of MassachusettsVerified email at cs.umass.edu
Scott NiekumAssociate Professor, University of Texas at AustinVerified email at cs.utexas.edu
Chris NotaUniversity of Massachusetts, AmherstVerified email at cs.umass.edu
Yuriy BrunManning College of Information and Computer Sciences, University of Massachusetts AmherstVerified email at cs.umass.edu
Sridhar MahadevanDirector, Data Science Lab, Adobe Research & Professor, University of Massachusetts, AmherstVerified email at cs.umass.edu
Will DabneyDeepMindVerified email at google.com
Sarah OsentoskiIron OxVerified email at ironox.com
Erik Learned-MillerProfessor of Computer Science, University of Massachusetts AmherstVerified email at cs.umass.edu
Robert KirschProfessor and Chair of Biomedical Engineering, Case Western Reserve UniversityVerified email at case.edu
Georg OstrovskiGoogle DeepMindVerified email at google.com
Arthur GuezGoogle DeepMindVerified email at google.com
Rémi MunosDeepMindVerified email at inria.fr

Philip Thomas

University of Massachusetts Amherst

Verified email at cs.umass.edu - Homepage

Artificial Intelligence Reinforcement Learning AI Safety


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
Data-efficient off-policy policy evaluation for reinforcement learning P Thomas, E Brunskill International Conference on Machine Learning, 2139-2148, 2016	371	2016
Value function approximation in reinforcement learning using the Fourier basis G Konidaris, S Osentoski, P Thomas Twenty-fifth AAAI conference on artificial intelligence, 2011	364	2011
High-confidence off-policy evaluation P Thomas, G Theocharous, M Ghavamzadeh Proceedings of the AAAI Conference on Artificial Intelligence 29 (1), 2015	221	2015
High confidence policy improvement P Thomas, G Theocharous, M Ghavamzadeh International Conference on Machine Learning, 2380-2388, 2015	166	2015
Personalized ad recommendation systems for life-time value optimization with guarantees G Theocharous, PS Thomas, M Ghavamzadeh Twenty-Fourth International Joint Conference on Artificial Intelligence, 2015	134	2015
Increasing the action gap: New operators for reinforcement learning MG Bellemare, G Ostrovski, A Guez, P Thomas, R Munos Proceedings of the AAAI Conference on Artificial Intelligence 30 (1), 2016	126	2016
Bias in natural actor-critic algorithms P Thomas International conference on machine learning, 441-448, 2014	123	2014
Learning action representations for reinforcement learning Y Chandak, G Theocharous, J Kostas, S Jordan, P Thomas International conference on machine learning, 941-950, 2019	100	2019
Preventing undesirable behavior of intelligent machines P Thomas, B Castro da Silva, A Barto, S Giguere, Y Brun, E Brunskill Science 366 (6468), 999-1004, 2019	94	2019
Safe reinforcement learning PS Thomas	83	2015
Proximal reinforcement learning: A new theory of sequential decision making in primal-dual spaces S Mahadevan, B Liu, P Thomas, W Dabney, S Giguere, N Jacek, I Gemp, ... arXiv preprint arXiv:1405.6757, 2014	47	2014
Use of atrial and bifocal cardiac pacemakers for treating resistant dysrhythmias. LS Dreifus, BV Berkovits, D Kimibiris, K Moghadam, G Haupt, P Walinsky, ... European Journal of Cardiology 3 (4), 257-266, 1975	45	1975
Training an actor-critic reinforcement learning controller for arm movement using human-generated rewards KM Jagodnik, PS Thomas, AJ van den Bogert, MS Branicky, RF Kirsch IEEE Transactions on Neural Systems and Rehabilitation Engineering 25 (10 …, 2017	44	2017
Using options and covariance testing for long horizon off-policy policy evaluation Z Guo, PS Thomas, E Brunskill Advances in Neural Information Processing Systems 30, 2017	40	2017
Predictive off-policy policy evaluation for nonstationary decision problems, with applications to digital marketing PS Thomas, G Theocharous, M Ghavamzadeh, I Durugkar, E Brunskill Twenty-Ninth IAAI Conference, 2017	37	2017
Application of the actor-critic architecture to functional electrical stimulation control of a human arm PS Thomas, A van den Bogert, K Jagodnik, M Branicky Twenty-First IAAI Conference, 2009	35	2009
Policy gradient methods for reinforcement learning with function approximation and action-dependent baselines PS Thomas, E Brunskill arXiv preprint arXiv:1706.06643, 2017	34	2017
Importance Sampling for Fair Policy Selection. S Doroudi, PS Thomas, E Brunskill Grantee Submission, 2017	33	2017
Some recent applications of reinforcement learning AG Barto, PS Thomas, RS Sutton Proceedings of the Eighteenth Yale Workshop on Adaptive and Learning Systems, 2017	32	2017
Projected natural actor-critic PS Thomas, WC Dabney, S Giguere, S Mahadevan Advances in neural information processing systems 26, 2013	32	2013

The system can't perform the operation now. Try again later.

Articles 1–20

Citations per year

Duplicate citations

Merged citations

Add co-authorsCo-authors

Follow this author

Cited by

Co-authors