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 | 565 | 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 | 488 | 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 | 473 | 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 | 264 | 2011 |
Exploration from Demonstration for Interactive Reinforcement Learning K Subramanian, CL Isbell Jr, AL Thomaz AAMAS, 2016 | 112 | 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 | 32 | 2012 |
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 | 29 | 2014 |
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 |
Robot learning from demonstration: kinesthetic teaching vs. teleoperation B Akgun, K Subramanian Unpublished manuscript 26, 2011 | 23 | 2011 |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, A Thomaz Proceedings of the AAAI Conference on Artificial Intelligence 25 (1), 1868-1869, 2011 | 8 | 2011 |
Systems and methods for generating instructions for navigating intersections with autonomous vehicles D Isele, G Rahimi, A Cosgun, K Subramanian, K Fujimura US Patent 11,480,971, 2022 | 7 | 2022 |
Task space behavior learning for humanoid robots using Gaussian mixture models K Subramanian Proceedings of the AAAI Conference on Artificial Intelligence 24 (1), 1961-1962, 2010 | 7 | 2010 |
Implementation Of FPGA-based Object Tracking Algorithm G Shrikanth, K Subramanian Undergraduate Project Report, SVCE, Tamil Nadu, India, 2008 | 7 | 2008 |
Policy Shaping in Domains with Multiple Optimal Policies H Sahni, B Harrison, K Subramanian, T Cederborg, C Isbell, A Thomaz AAMAS, 2016 | 6 | 2016 |
A Super-human Vision-based Reinforcement Learning Agent for Autonomous Racing in Gran Turismo M Vasco, T Seno, K Kawamoto, K Subramanian, PR Wurman, P Stone Reinforcement Learning Conference, 2024 | 2 | 2024 |
SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning H Lee, D Hwang, D Kim, H Kim, JJ Tai, K Subramanian, PR Wurman, ... arXiv preprint arXiv:2410.09754, 2024 | 1 | 2024 |
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, School of Graduate Studies, 2010 | 1 | 2010 |