Todd Hester
Ph.D. Student (Alumni)
Todd's research focused reinforcement learning and robotics, specifically looking at the exploration versus exploitation problem in reinforcement learning and working to apply it to large domains. Before coming to UT, Todd worked in the Motion Analysis Laboratory at Spaulding Rehabiliation Hospital, Motorola, Sun Microsystems, and the Air Force Research Laboratory. Outside of his research, Todd enjoys ultimate frisbee and foosball and is a dedicated New England Patriots fan.
Homepage:
http://www.cs.utexas.edu/~todd
Publications (21)
Learning Exploration Strategies in Model-Based Reinforcement Learning 2013
Todd Hester and Manuel Lopes and Peter Stone
UT Austin Villa 2012: Standard Platform League World Champions 2013
Samuel Barrett, Katie Genter, Yuchen He, Todd Hester, Piyush Khandelwal, Jacob Menashe, and Peter Stone
Intrinsically Motivated Model Learning for a Developing Curious Agent 2012
Todd Hester and Peter Stone
Intrinsically Motivated Model Learning for a Developing Curious Agent 2012
Todd Hester and Peter Stone
TEXPLORE: Temporal Difference Reinforcement Learning for Robots and Time-Constrained Domains. 2012
Todd Hester
{A}ustin {V}illa 2011: Sharing is Caring: Better Awareness through Information Sharing 2012
Samuel Barrett and Katie Genter and Todd Hester and Piyush Khandelwal and Michael Quinlan and Peter Stone and Mohan Sridharan
{RTMBA}: A Real-Time Model-Based Reinforcement Learning Architecture for Robot Control 2012
Todd Hester and Michael Quinlan and Peter Stone
{TEXPLORE}: Real-Time Sample-Efficient Reinforcement Learning for Robots 2012
Todd Hester and Peter Stone
A Real-Time Model-Based Reinforcement Learning Architecture for Robot Control 2011
Todd Hester and Michael Quinlan and Peter Stone
Austin Villa 2010 Standard Platform Team Report 2011
Samuel Barrett and Katie Genter and Matthew Hausknecht and Todd Hester and Piyush Khandelwal and Juhyun Lee and Michael Quinlan and Aibo Tian and Peter Stone and Mohan Sridharan
Learning and Using Models 2011
Todd Hester and Peter Stone
Controlled Kicking under Uncertainty 2010
Samuel Barrett and Katie Genter and Todd Hester and Michael Quinlan and Peter Stone
Generalized Model Learning for Reinforcement Learning on a Humanoid Robot 2010
Todd Hester and Michael Quinlan and Peter Stone
Real Time Targeted Exploration in Large Domains 2010
Todd Hester and Peter Stone
An Empirical Comparison of Abstraction in Models of Markov Decision Processes 2009
Todd Hester and Peter Stone
Generalized Model Learning for Reinforcement Learning in Factored Domains 2009
Todd Hester and Peter Stone
Three Humanoid Soccer Platforms: Comparison and Synthesis 2009
Shivaram Kalyanakrishnan and Todd Hester and Michael Quinlan and Yinon Bentor and Peter Stone
TT-UT Austin Villa 2009: Naos across Texas 2009
Todd Hester and Michael Quinlan and Peter Stone and Mohan Sridharan
Negative Information and Line Observations for Monte Carlo Localization 2008
Todd Hester and Peter Stone
The Utility of Temporal Abstraction in Reinforcement Learning 2008
Nicholas K. Jong and Todd Hester and Peter Stone
UT Austin Villa 2008: Standing on Two Legs 2008
Todd Hester, Michael Quinlan, and Peter Stone
Projects
TEXPLORE: Real-Time Sample Efficient Reinforcement Learning 2009 - Present
The UT Austin Villa Robot Soccer team 2003 - Present
Areas of Interest
Reinforcement Learning Robotics Robot Soccer Real Robot Soccer RoboCup
Demos
TEXPLORE: Real-Time Sample Efficient Reinforcement LearningTodd Hester2012
SPL Robocup Soccer2008
Labs
Learning Agents