| Policy shaping: Integrating human feedback with reinforcement learning S Griffith, K Subramanian, J Scholz, C Isbell, AL Thomaz Advances in Neural Information Processing Systems, 2625-2633, 2013 | 490 | 2013 |
| Navigating Occluded Intersections with Autonomous Vehicles using Deep Reinforcement Learning D Isele, R Rahimi, A Cosgun, K Subramanian, K Fujimura arXiv preprint arXiv:1705.01196, 2017 | 431 | 2017 |
| Outracing champion Gran Turismo drivers with deep reinforcement learning PR Wurman, S Barrett, K Kawamoto, J MacGlashan, K Subramanian, ... Nature 602 (7896), 223-228, 2022 | 349 | 2022 |
| Apprenticeship learning about multiple intentions M Babes, V Marivate, K Subramanian, ML Littman Proceedings of the 28th International Conference on Machine Learning (ICML …, 2011 | 247 | 2011 |
| Exploration from Demonstration for Interactive Reinforcement Learning K Subramanian, CL Isbell Jr, AL Thomaz AAMAS, 2016 | 104 | 2016 |
| Generalizing apprenticeship learning across hypothesis classes TJ Walsh, K Subramanian, ML Littman, C Diuk Proceedings of the 27th International Conference on Machine Learning (ICML …, 2010 | 37 | 2010 |
| Novel Interaction Strategies for Learning from Teleoperation. B Akgun, K Subramanian, AL Thomaz AAAI Fall Symposium: Robots Learning Interactively from Human Teachers, 2012 | 31 | 2012 |
| Learning options through human interaction K Subramanian, C Isbell, A Thomaz 2011 IJCAI Workshop on Agents Learning Interactively from Human Teachers (ALIHT), 2011 | 27 | 2011 |
| Abstraction from demonstration for efficient reinforcement learning in high-dimensional domains LC Cobo, K Subramanian, CL Isbell Jr, AD Lanterman, AL Thomaz Artificial Intelligence 216, 103-128, 2014 | 25 | 2014 |
| Robot learning from demonstration: kinesthetic teaching vs. teleoperation B Akgun, K Subramanian Unpublished manuscript, 26, 2011 | 19 | 2011 |
| Efficient exploration in monte carlo tree search using human action abstractions K Subramanian, J Scholz, CL Isbell, AL Thomaz Future of Interactive Machine Learning Workshop at the 30th International …, 2016 | 9 | 2016 |
| Learning tasks and skills together from a human teacher B Akgun, K Subramanian, J Shim, AL Thomaz Twenty-Fifth AAAI Conference on Artificial Intelligence, 2011 | 8 | 2011 |
| Task space behavior learning for humanoid robots using Gaussian mixture models K Subramanian Twenty-Fourth AAAI Conference on Artificial Intelligence, 2010 | 7 | 2010 |
| Implementation Of FPGA-based Object Tracking Algorithm G Shrikanth, K Subramanian Undergraduate Project Report, SVCE, Tamil Nadu, India, 2008 | 7 | 2008 |
| Systems and methods for generating instructions for navigating intersections with autonomous vehicles D Isele, R Rahimi, A Cosgun, K Subramanian, K Fujimura US Patent App. 15/968,460, 2019 | 6 | 2019 |
| Policy Shaping in Domains with Multiple Optimal Policies H Sahni, B Harrison, K Subramanian, T Cederborg, C Isbell, A Thomaz AAMAS, 2016 | 6 | 2016 |
| Multi-forecast networks R Capobianco, V Kompella, K Subramanian, J Macglashan, P Wurman, ... US Patent App. 16/732,918, 2020 | 1 | 2020 |
| HELP—Human assisted Efficient Learning Protocols K Subramanian Rutgers The State University of New Jersey-New Brunswick, 2010 | 1 | 2010 |
| Policy-based Exploration for Efficient Reinforcement Learning K Subramanian Georgia Institute of Technology, 2020 | | 2020 |
| Method and system for continual learning in an intelligent artificial agent MB Ring, S BAVEJA, R CAPOBIANCO, V KOMPELLA, K Subramanian, ... US Patent US20200074349A1, 2020 | | 2020 |
Andrea ThomazInteractive Computing, Georgia Institute of Technology在 ece.utexas.edu 的电子邮件经过验证
