Shivaram Kalyanakrishnan
Hello! I am a graduate student in the Department of Computer Sciences at the University of Texas at Austin. I joined the department in August 2004, and am enrolled for a Ph.D. I am advised by Peter Stone, who leads the Learning Agents Research Group. My primary area of research is machine learning; more specifically, I'm interested in empirical studies in the area of reinforcement learning. I use Robot Soccer as a test domain for my research, and am part of the UT Austin Villa robot soccer team.
I organise meetings of the UTCS Reinforcement Learning Reading Group.
This page lists my research interests and relevant academic information. I'm always happy to correspond through e-mail about topics concerning my research!
Research Interests
I believe that it is possible to represent "intelligent behaviour" as a computer program. Crucial to the sustenance of an intelligent agent situated in a realistic environment is its ability to learn and adapt to that environment. Reinforcement Learning provides a framework to model an agent that can improve its behaviour based on the experience it gathers by interacting with the environment.
The reinforcement learning problem is broad in its scope, encompassing a variety of realistic scenarios in a natural and elegant manner. Nevertheless, complex real-world problems often violate the assumptions that form the basis of traditional solutions to the reinforcement learning problem. Solutions to many problems of practical interest invariably demand the application of engineering approaches that exploit their underlying structure. Identifying techniques to solve complex reinforcement learning problems constitutes the broad scope of my research. Below is a list of my publications, along with abstracts and auxiliary material.
Publications
-
Three Humanoid Soccer Platforms: Comparison and Synthesis
Shivaram Kalyanakrishnan, Todd Hester, Michael Quinlan, Yinon Bentor and Peter Stone
In Proceedings
of the RoboCup International Symposium 2009. To appear as
short paper.
PS, PDF, Abstract and BibTeX
-
Learning Complementary Multiagent Behaviors: A Case Study
Shivaram Kalyanakrishnan and Peter Stone
In Proceedings
of the RoboCup International Symposium 2009. To appear.
PS, PDF, Abstract and BibTeX
A similiar version of this paper was accepted at
the Adaptive and Learning Agents Workshop at AAMAS 2009, Budapest, Hungary. A short version is to appear in Proceedings of the Eighth International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2009).
Supplementary videos available at
the UT
Austin Villa Keepaway GetOpen page.
-
An Empirical Analysis of Value Function-Based and Policy Search Reinforcement Learning
Shivaram Kalyanakrishnan and Peter Stone
In Proceedings of the Eighth International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2009). To appear.
PS, PDF, Abstract and BibTeX
-
The UT Austin Villa 3D Simulation Soccer Team 2008
Shivaram Kalyanakrishnan, Yinon Bentor and Peter Stone
Technical Report AI09-01, The University of Texas at Austin, Department of Computer Sciences, AI Laboratory, 2009.
PS, PDF, Abstract and BibTeX
Supplementary binary and videos available at the UT Austin Villa 3D Simulation page.
-
The UT Austin Villa 3D Simulation Soccer Team 2007
Shivaram Kalyanakrishnan and Peter Stone
Technical Report AI07-348, The University of Texas at Austin, Department of Computer Sciences, AI Laboratory, 2007.
PS, PDF, Abstract and BibTeX
Supplementary binary and videos available at the UT Austin Villa 3D Simulation page.
-
Model-based Reinforcement Learning in a Complex Domain
Shivaram Kalyanakrishnan, Peter Stone and Yaxin Liu
In Ubbo Visser, Fernando Ribeiro, Takeshi Ohashi, and Frank Dellaert, editors, RoboCup 2007: Robot Soccer World Cup XI, Springer Verlag, Berlin, 2008. pp. 171-183.
PS, PDF, Abstract and BibTeX
-
Batch Reinforcement Learning in a Complex Domain
Shivaram Kalyanakrishnan and Peter Stone
In Proceedings of the Sixth International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS 2007), ACM, New York, NY, USA, 2007. pp. 650-657.
Nominee for Best Student Paper Award at AAMAS 2007, Honolulu, Hawai'i, U.S.A.
PS, PDF, Abstract and BibTeX
-
Half Field Offense in RoboCup Soccer: A Multiagent Reinforcement Learning Case Study
Shivaram Kalyanakrishnan, Yaxin Liu and Peter Stone
In Gerhard Lakemeyer, Elizabeth Sklar, Domenico Sorenti, and Tomoichi Takahashi, editors, RoboCup 2006: Robot Soccer World Cup X, Springer Verlag, Berlin, 2007. pp. 72-85.
Winner of Best Student Paper Award at the RoboCup International Symposium 2006, Bremen, Germany.
PS, PDF, Abstract and BibTeX
Supplementary videos available at the UT Austin Villa Half Field Offense page.
Professional Activities
- Invited Talk: Interactive Intelligence Lab, IIT Madras, 2009.
- Invited Reviewer: RoboCup Internatonal Symposium 2009, 2009.
- Invited Reviewer: 26th International Conference on Machine Learning, 2009.
- Invited Reviewer: Journal of Artificial Intelligence Research, 2008.
- Professional Internship: Honda Research Institute, 2008.
- Invited Reviewer: Tenth International Conference on Intelligent Autonomous Systems, 2008.
- Member of Technical Committee, Second Annual Reinforcement Learning Competition, 2008.
- Member of UT Austin Villa team, RoboCup 3D Simulation Competition, 2008.
- Member of LARG team: 1st place, Tetris Event, First Annual Reinforcement Learning Competition, 2007.
- Member of UT Austin Villa team, RoboCup 3D Simulation Competition, 2007.
- Member of UT Austin Villa team: 2nd place, RoboCup Simulation Coach Competition, 2006.
- Invited Reviewer: AAMAS 2006 Workshop on Adaptation and Learning in Autonomous Agents and Multiagent Systems, 2006.
- Coordinator: UTCS Reinforcement Learning Reading Group, 2006 - present.
- Professional Internship: Tejas Networks, 2003.
Course Work at UT Austin
- HIS 350L: History of Imperialism (Tony Hopkins, Fall 2007)
- GRC 301: Bad Boy Brecht (Martin Kley, Spring 2007)
- CS 380D: Distributed Computing I (Jayadev Misra, Fall 2006)
- CS 386L: Programming Languages (William Cook, Spring 2006)
- CS 384G: Computer Graphics (Bill Mark, Fall 2005)
- CS 395T: Computational Learning Theory (Adam Klivans, Fall 2005)
- CS 383D: Numerical Analysis: Interpolation, Approximation, Quadrature, Differential Equations (Alan Cline, Spring 2005)
- CS 394F: Knowledge Representation ad Reasoning (Bruce Porter, Spring 2005)
- CS 388L: Introduction to Mathematical Logic (Vladimir Lifschitz, Fall 2004)
- CS 391L: Machine Learning (Ray Mooney, Fall 2004)
- CS 398T: Supervised Teaching in Computer Science (Roger Priebe, Fall 2004)
Academic Background
Contact Information
Shivaram Kalyanakrishnan
Office: ENS 32SE06
E-mail: shivaram@cs.utexas.edu
Address: 1 University Station, C0500, Taylor Hall 2.124
Resources Related to My Research