Philip Thomas

Citirano

	Sve	Od 2020.
Citati	5133	3640
H-indeks	35	30
i10-indeks	61	52

800

400

200

600

20112012201320142015201620172018201920202021202220232024202518 36 35 43 73 139 188 257 425 588 679 732 793 755 93

Javni pristup

Prikaži sve

31 članak

1 članak

dostupno

nije dostupno

Na temelju uvjeta financiranja

Suautori

Georgios TheocharousAdobe ResearchPotvrđena adresa e-pošte na adobe.com
Emma BrunskillAssociate Professor of Computer Science, Stanford UniversityPotvrđena adresa e-pošte na cs.stanford.edu
Bruno Castro da SilvaUniversity of MassachusettsPotvrđena adresa e-pošte na cs.umass.edu
Scott M. JordanPostdoctoral Fellow, University of AlbertaPotvrđena adresa e-pošte na ualberta.ca
Scott NiekumAssociate Professor, University of Massachusetts AmherstPotvrđena adresa e-pošte na cs.umass.edu
Antonie J. (Ton) van den BogertProfessor of Mechanical Engineering, Cleveland State UniversityPotvrđena adresa e-pošte na csuohio.edu
George KonidarisBrownPotvrđena adresa e-pošte na cs.brown.edu
Stephen GiguereUniversity of MassachusettsPotvrđena adresa e-pošte na cs.umass.edu
Chris NotaUniversity of Massachusetts, AmherstPotvrđena adresa e-pošte na cs.umass.edu
Yuriy BrunManning College of Information and Computer Sciences, University of Massachusetts AmherstPotvrđena adresa e-pošte na cs.umass.edu
Michael BranickyProfessor of Electrical Engineering & Computer Science, University of KansasPotvrđena adresa e-pošte na ku.edu
Erik Learned-MillerProfessor of Computer Science, University of Massachusetts AmherstPotvrđena adresa e-pošte na cs.umass.edu
Blossom MetevierUniversity of Massachusetts AmherstPotvrđena adresa e-pošte na umass.edu
Sarah OsentoskiVinci4dPotvrđena adresa e-pošte na vinci4d.ai
Sridhar MahadevanDirector, Adobe Research & Professor, University of Massachusetts, AmherstPotvrđena adresa e-pošte na cs.umass.edu
Will DabneyDeepMindPotvrđena adresa e-pošte na google.com
Francisco M. GarciaUniversity of Massachusetts - AmherstPotvrđena adresa e-pošte na cs.umass.edu
Robert KirschProfessor and Chair of Biomedical Engineering, Case Western Reserve UniversityPotvrđena adresa e-pošte na case.edu
Peter StoneProfessor of Computer Science, The University of Texas at AustinPotvrđena adresa e-pošte na cs.utexas.edu
Arthur GuezGoogle DeepMindPotvrđena adresa e-pošte na google.com

Prati

Philip Thomas

University of Massachusetts Amherst

Potvrđena adresa e-pošte na cs.umass.edu - Početna stranica

Artificial Intelligence Reinforcement Learning AI Safety


Naslov Poredaj po navodima Poredaj po godini Poredaj po naslovu	Citirano Citirano	Godina
Data-efficient off-policy policy evaluation for reinforcement learning P Thomas, E Brunskill International conference on machine learning, 2139-2148, 2016	786	2016
Value function approximation in reinforcement learning using the Fourier basis G Konidaris, S Osentoski, P Thomas Proceedings of the AAAI conference on artificial intelligence 25 (1), 380-385, 2011	559	2011
High-confidence off-policy evaluation P Thomas, G Theocharous, M Ghavamzadeh Proceedings of the AAAI Conference on Artificial Intelligence 29 (1), 2015	346	2015
High confidence policy improvement P Thomas, G Theocharous, M Ghavamzadeh International Conference on Machine Learning, 2380-2388, 2015	230	2015
Learning action representations for reinforcement learning Y Chandak, G Theocharous, J Kostas, S Jordan, P Thomas International conference on machine learning, 941-950, 2019	221	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	210	2019
Ad recommendation systems for life-time value optimization G Theocharous, PS Thomas, M Ghavamzadeh Proceedings of the 24th international conference on world wide web, 1305-1310, 2015	209	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	183	2016
Bias in natural actor-critic algorithms P Thomas International conference on machine learning, 441-448, 2014	173	2014
Safe reinforcement learning PS Thomas University of Massachusetts Libraries, 2015	128	2015
Optimization and evaluation of a proportional derivative controller for planar arm movement KM Jagodnik, AJ van den Bogert Journal of Biomechanics 43 (6), 1086-1091, 2010	89	2010
Is the policy gradient a gradient? C Nota, PS Thomas arXiv preprint arXiv:1906.07073, 2019	86	2019
Evaluating the performance of reinforcement learning algorithms S Jordan, Y Chandak, D Cohen, M Zhang, P Thomas International Conference on Machine Learning, 4962-4973, 2020	79	2020
Optimizing for the future in non-stationary mdps Y Chandak, G Theocharous, S Shankar, M White, S Mahadevan, ... International Conference on Machine Learning, 1414-1425, 2020	79	2020
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	74	2017
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	74	2014
Policy gradient methods for reinforcement learning with function approximation and action-dependent baselines PS Thomas, E Brunskill arXiv preprint arXiv:1706.06643, 2017	73	2017
Predictive off-policy policy evaluation for nonstationary decision problems, with applications to digital marketing P Thomas, G Theocharous, M Ghavamzadeh, I Durugkar, E Brunskill Proceedings of the AAAI Conference on Artificial Intelligence 31 (2), 4740-4745, 2017	67	2017
Risk Quantification for Policy Deployment PS Thomas, G Theocharous, M Ghavamzadeh US Patent App. 14/552,047, 2016	65	2016
Offline contextual bandits with high probability fairness guarantees B Metevier, S Giguere, S Brockman, A Kobren, Y Brun, E Brunskill, ... Advances in neural information processing systems 32, 2019	63	2019

Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.

Članci 1–20

Godišnji broj citata

Dvostruki navodi

Spojeni navodi

Dodavanje suautoraSuautori

Prati

Citirano

Suautori