Robert Loftin
Robert Loftin
Post-Doc, Microsoft Research Cambridge
Verified email at ncsu.edu
Title
Cited by
Cited by
Year
Interactive learning from policy-dependent human feedback
J MacGlashan, MK Ho, R Loftin, B Peng, G Wang, DL Roberts, ME Taylor, ...
International Conference on Machine Learning, 2285-2294, 2017
1152017
Improving developer participation rates in surveys
E Smith, R Loftin, E Murphy-Hill, C Bird, T Zimmermann
2013 6th International workshop on cooperative and human aspects of software …, 2013
872013
Toward cyber-enhanced working dogs for search and rescue
A Bozkurt, DL Roberts, BL Sherman, R Brugarolas, S Mealin, J Majikes, ...
IEEE Intelligent Systems 29 (6), 32-39, 2014
822014
Learning behaviors via human-delivered discrete feedback: modeling implicit feedback strategies to speed up learning
R Loftin, B Peng, J MacGlashan, ML Littman, ME Taylor, J Huang, ...
Autonomous agents and multi-agent systems 30 (1), 30-59, 2016
782016
A strategy-aware technique for learning behaviors from discrete human feedback
R Loftin, J MacGlashan, B Peng, M Taylor, M Littman, J Huang, D Roberts
Proceedings of the AAAI Conference on Artificial Intelligence 28 (1), 2014
602014
Behavior recognition based on machine learning algorithms for a wireless canine machine interface
R Brugarolas, RT Loftin, P Yang, DL Roberts, B Sherman, A Bozkurt
2013 IEEE international conference on body sensor networks, 1-5, 2013
542013
A need for speed: Adapting agent action speed to improve task learning from non-expert humans
B Peng, J MacGlashan, R Loftin, ML Littman, DL Roberts, ME Taylor
Proceedings of the International Joint Conference on Autonomous Agents and …, 2016
402016
Better Exploration with Optimistic Actor-Critic
K Ciosek, Q Vuong, R Loftin, K Hofmann
arXiv preprint arXiv:1910.12807, 2019
262019
Learning something from nothing: Leveraging implicit human feedback strategies
R Loftin, B Peng, J MacGlashan, ML Littman, ME Taylor, J Huang, ...
The 23rd IEEE International Symposium on Robot and Human Interactive …, 2014
222014
Training an agent to ground commands with reward and punishment
J MacGlashan, ML Littman, R Loftin, B Peng, D Roberts, ME Taylor
Proceedings of the AAAI Machine Learning for Interactive Systems Workshop, 6-12, 2014
202014
An empirical study of non-expert curriculum design for machine learners
B Peng, J MacGlashan, R Loftin, ML Littman, DL Roberts, ME Taylor
In Proceedings of the IJCAI Interactive Machine Learning Workshop, 2016
122016
Curriculum design for machine learners in sequential decision tasks
B Peng, J MacGlashan, R Loftin, ML Littman, DL Roberts, ME Taylor
IEEE Transactions on Emerging Topics in Computational Intelligence 2 (4 …, 2018
92018
Convergent actor critic by humans
J MacGlashan, ML Littman, DL Roberts, R Loftin, B Peng, ME Taylor
International Conference on Intelligent Robots and Systems, 2016
52016
Language and policy learning from human-delivered feedback
B Peng, R Loftin, J MacGlashan, ML Littman, ME Taylor, DL Roberts
Machine Learning for Social Robotics Workshop, 2015 International Conference …, 2015
42015
Open Problems for Online Bayesian Inference in Neural Networks
R Loftin, ME Taylor, ML Littman, J MacGlashan, B Peng, DL Roberts
Bayesian Deep Learning Workshop at NeurIPS, 2016
12016
Interactive Learning of Environment Dynamics for Sequential Tasks
R Loftin, B Peng, ME Taylor, ML Littman, DL Roberts
arXiv preprint arXiv:1907.08478, 2019
2019
Extracting Latent Knowledge to Reduce Teacher Effort in Interactive Machine Learning.
RT Loftin
2019
Towards Behavior-Aware Model Learning from Human-Generated Trajectories.
RT Loftin, J MacGlashan, B Peng, ME Taylor, ML Littman, DL Roberts
AAAI Fall Symposia, 2016
2016
A Proposal for Behavior Prediction via Estimating Agents’ Evaluation Functions Using Prior Observations of Behavior
RT Loftin, DL Roberts
Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015
2015
An Empirical Analysis of RL’s Drift From Its Behaviorism Roots
M Adams, R Loftin, ME Taylor, M Littman, D Roberts
2012
The system can't perform the operation now. Try again later.
Articles 1–20