W Bradley Knox

Cited by

	All	Since 2020
Citations	4503	2833
h-index	25	20
i10-index	37	28

740

370

185

555

2009201020112012201320142015201620172018201920202021202220232024202524 27 56 68 119 147 140 212 216 306 297 416 465 468 572 739 166

Public access

View all

6 articles

0 articles

available

not available

Based on funding mandates

Co-authors

Peter StoneProfessor of Computer Science, The University of Texas at AustinVerified email at cs.utexas.edu
Scott NiekumAssociate Professor, University of Massachusetts AmherstVerified email at cs.umass.edu
Cynthia BreazealProfessor Media Arts and Sciences, MIT Media LabVerified email at media.mit.edu
Maya CakmakUniversity of WashingtonVerified email at cs.washington.edu
Alessandro AllieviImperial College LondonVerified email at imperial.ac.uk
Todd KuleszaUser Experience Researcher, GoogleVerified email at google.com
Saleema AmershiMicrosoft ResearchVerified email at microsoft.com
Bradley C. LoveSenior Research Scientist, Los Alamos National Laboratory. Former utexas.edu and ucl.ac.uk prof.Verified email at lanl.gov
Serena BoothBrown UniversityVerified email at brown.edu
Hayley HungAssociate Professor, Delft University of TechnologyVerified email at tudelft.nl
Shimon WhitesonProfessor of Computer Science, University of Oxford / Senior Staff Research Scientist, WaymoVerified email at cs.ox.ac.uk
Guangliang LiAssociate Professor, College of Electrical Engineering, Ocean University of China, Qingdao, ChinaVerified email at ouc.edu.cn
Ross OttoDepartment of Psychology, McGill UniversityVerified email at mcgill.ca
Jin Joo Lee, PhDAmazon Lab126Verified email at amazon.com
Rafael Mitkov RafailovGraduate Student, Stanford UniversityVerified email at stanford.edu
Chelsea FinnStanford University, Physical IntelligenceVerified email at cs.stanford.edu
Harshit SikchiUniversity of Texas at AustinVerified email at cs.utexas.edu
Joey HejnaStanford UniversityVerified email at stanford.edu
Felix SchmittBosch Center for Artificial IntelligenceVerified email at de.bosch.com
W. Todd MaddoxWayne Holtzman Chair and Professor of Psychology, University of TexasVerified email at utexas.edu

W Bradley Knox

Research Associate Professor at UT Austin

Verified email at cs.utexas.edu - Homepage

Reward functions Alignment RLHF Reinforcement Learning Human-Robot Interaction


Title Sort by citations Sort by year Sort by title	Cited by Cited by	Year
Power to the people: The role of humans in interactive machine learning S Amershi, M Cakmak, WB Knox, T Kulesza AI Magazine 35 (4), 105-120, 2014	1324	2014
Interactively shaping agents via human reinforcement: The TAMER framework WB Knox, P Stone Proceedings of the 5th International Conference on Knowledge Capture (K-CAP …, 2009	660	2009
Reinforcement learning from simultaneous human and MDP reward WB Knox, P Stone Proceedings of the 11th International Conference on Autonomous Agents and …, 2012	304*	2012
Combining manual feedback with subsequent MDP reward signals for reinforcement learning WB Knox, P Stone Proceedings of the 9th International Conference on Autonomous Agents and …, 2010	281	2010
Tamer: Training an agent manually via evaluative reinforcement WB Knox, P Stone 2008 7th IEEE international conference on development and learning, 292-297, 2008	233	2008
Training a robot via human feedback: A case study WB Knox, P Stone, C Breazeal International Conference on Social Robotics (ICSR), 460-470, 2013	184	2013
Computationally modeling interpersonal trust JJ Lee, B Knox, J Baumann, C Breazeal, D DeSteno Frontiers in psychology 4, 56004, 2013	136	2013
Reward (Mis)design for Autonomous Driving WB Knox, A Allievi, H Banzhaf, F Schmitt, P Stone arXiv preprint arXiv:2104.13906, 2021	135	2021
The nature of belief-directed exploratory choice in human decision-making WB Knox, AR Otto, P Stone, B Love Frontiers in Psychology 2, 2012	104	2012
How humans teach agents: A new experimental perspective WB Knox, BD Glass, BC Love, WT Maddox, P Stone International Journal of Social Robotics 4 (4), 409-421, 2012	98	2012
The perils of trial-and-error reward design: misdesign through overfitting and invalid task specifications S Booth, WB Knox, J Shah, S Niekum, P Stone, A Allievi Proceedings of the AAAI Conference on Artificial Intelligence 37 (5), 5920-5929, 2023	84	2023
Framing reinforcement learning from human reward: Reward positivity, temporal discounting, episodicity, and performance WB Knox, P Stone Artificial Intelligence 225, 24-50, 2015	82	2015
The EMPATHIC Framework for Task Learning from Implicit Human Feedback Y Cui, Q Zhang, A Allievi, P Stone, S Niekum, WB Knox Conference on Robot Learning (CoRL), 2020	80	2020
Reinforcement Learning from Human Reward: Discounting in Episodic Tasks WB Knox, P Stone 21st IEEE International Symposium on Robot and Human Interactive …, 2012	80	2012
Learning from Human-Generated Reward WB Knox University of Texas at Austin, 2012	60	2012
Contrastive preference learning: Learning from human feedback without RL J Hejna, R Rafailov, H Sikchi, C Finn, S Niekum, WB Knox, D Sadigh arXiv preprint arXiv:2310.13639, 2023	56	2023
Learning non-myopically from human-generated reward WB Knox, P Stone Proceedings of the 2013 international conference on Intelligent user …, 2013	47	2013
Know thine enemy: A champion RoboCup coach agent G Kuhlmann, WB Knox, P Stone Proceedings of the National Conference on Artificial Intelligence 21 (2), 1463, 2006	47	2006
Models of human preference for learning reward functions WB Knox, S Hatgis-Kessell, S Booth, S Niekum, P Stone, A Allievi arXiv preprint arXiv:2206.02231, 2022	46	2022
Scaling laws for reward model overoptimization in direct alignment algorithms R Rafailov, Y Chittepu, R Park, HS Sikchi, J Hejna, B Knox, C Finn, ... Advances in Neural Information Processing Systems 37, 126207-126242, 2024	45	2024

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

Cited by

Co-authors