Home          Experience          Research          Teaching          Publications   

Journal Papers

Peter R. Wurman, Samuel Barrett, Kenta Kawamoto, James MacGlashan, Kaushik Subramanian, Thomas J. Walsh, Roberto Capobianco, Alisa Devlic, Franziska Eckert, Florian Fuchs, Leilani Gilpin, Piyush Khandelwal, Varun Kompella, HaoChih Lin, Patrick MacAlpine, Declan Oller, Takuma Seno, Craig Sherstan, Michael D. Thomure, Houmehr Aghabozorgi, Leon Barrett, Rory Douglas, Dion Whitehead, Peter Duerr, Peter Stone, Michael Spranger & Hiroaki Kitano: Outracing Champion Gran Turismo Drivers with Deep Reinforcement Learning. Appeared in the Nature journal, Feb 2022 edition. Link

Luis C. Cobo, Kaushik Subramanian, Charles L. Isbell, Aaron D. Lanterman, Andrea L. Thomaz: Abstraction from Demonstration for Efficient Reinforcement Learning in High-Dimensional Domains. Appeared in the Artificial Intelligence Journal (AIJ) 2014. Link


Conference Papers

Kaushik Subramanian, Charles L. Isbell, Andrea L. Thomaz: Exploration from Demonstration for Interactive Reinforcement Learning. Appeared in AAMAS 2016, Singapore, May 2016. Pdf

(Extended Abstract) Himanshu Sahni, Brent Harrison, Kaushik Subramanian, Thomas Cederborg, Charles L. Isbell, Andrea L. Thomaz: Policy Shaping in Domains with Multiple Optimal Policies. Appeared in AAMAS 2016, Singapore, May 2016. Pdf

• Also appeared in the IJCAI 2016 Interactive Machine Learning Workshop in New York, July 2016. Pdf
  

Shane Griffith, Kaushik Subramanian, Jonathan Scholz, Charles L. Isbell, Andrea L. Thomaz: Policy Shaping: Integrating Human Feedback with Reinforcement Learning. Appeared in NIPS 2013, Lake Tahoe, Nevada, USA, December 2013. Pdf

• Also appeared in RLDM 2013, Princeton, New Jersey, USA, Oct 2013. One of four papers, out of 150 submissions, given an oral presentation slot.
  

Monica Babes-Vroman, Vukosi Marivate, Kaushik Subramanian, Michael L. Littman: Apprenticeship Learning about Multiple Intentions. Appeared in ICML 2011, Bellevue, Washington, USA, June 2011. Pdf

• Also appeared in the NYAS 2010 Machine Learning Workshop in New York, USA, Oct 2010.

Thomas J. Walsh, Kaushik Subramanian, Michael L. Littman, Carlos Diuk: Generalizing Apprenticeship Learning across Hypothesis Classes. Appeared in ICML 2010, Haifa, Israel, June 2010. Pdf

• Also appeared in the AAMAS 2010 ALIHT Workshop in Toronto, Canada, May 2010.
  

Workshop Papers

Kaushik Subramanian, Jonathan Scholz, Charles L. Isbell, Andrea L. Thomaz: Efficient Exploration in Monte Carlo Tree Search using Human Action Abstractions. Appeared in the FILM Workshop at NIPS 2016, Barcelona, Spain, December 2016. Pdf

Baris Akgun, Kaushik Subramanian, Andrea L. Thomaz: Novel Interaction Strategies for Learning from Teleoperation. Appeared in the RLIHT Symposium at AAAI 2012, Virginia, USA, November 2nd 2012. Pdf

Kaushik Subramanian, Charles L. Isbell, Andrea L. Thomaz: Learning Options through Human Interaction. Appeared in the IJCAI ALIHT Workshop 2011, Barcelona, Spain, July 2011. Pdf

Kaushik Subramanian: Task Space Behavior Learning for Humanoid Robots using Gaussian Mixture Regression. Appeared in AAAI 2010, Atlanta, USA, July 2010. Pdf

Kaushik Subramanian: Higher Order Gabor Statistics for Speech and Image Signal Feature Extraction. Presented at Dhi Yantra 2008, Workshop on Supercomputing and Brain Modeling conducted by WARFT, India.


Technical Reports

Baris Akgun, Kaushik Subramanian, Jaeeun Shim, Andrea L.  Thomaz: Learning Tasks and Skills Together From a Human Teacher. Appeared in AAAI 2011, San Francisco, USA, August 7th 2011. Pdf

Kaushik Subramanian and Michael Littman: Efficient Apprenticeship Learning with Smart Humans. Appeared in the Robotics Exhibition, AAAI 2010, Atlanta, USA, July 2010. Pdf

Kaushik Subramanian, Gerhard Lakemeyer: Robot Learning by Demonstration.  RWTH Technical Report, August 2009. Pdf

Shrikanth Ganapathy, Kaushik Subramanian: Implementation of FPGA-based Object Tracking Algorithm. Undergraduate Project Report, SVCE, Tamil Nadu, India, May 2008. Pdf

Kaushik Subramanian and N. Venkateswaran: Computationally Efficient Gabor Transform and its application for extracting Dominant Speech Signal Harmonics, WARFT Research Foundation, May 2008. Pdf


Dissertations

Policy-based Exploration for Efficient Reinforcement Learning
Kaushik Subramanian
Doctoral Thesis, Georgia Institute of Technology, May 2017. Pdf

HELP - Human assisted Efficient Learning Protocols
Kaushik Subramanian
Master's Thesis, Rutgers University, May 2010. Pdf