Advisory Board

Professor Peter Stone

Peter Stone, Ph.D. is an Alfred P. Sloan Research Fellow and Associate Professor in the Department of Computer Sciences at the University of Texas at Austin. He earned his Ph.D. in 1998 and his M.S. in 1995 from Carnegie Mellon University, both in Computer Science. He earned his B.S. in Mathematics from the University of Chicago in 1993. From 1999 to 2002 he was a Senior Technical Staff Member in the Artificial Intelligence Principles Research Department at AT&T Labs Research. He is on the Editorial Boards of Artificial Intelligence Journal (AIJ), Journal of Autonomous Agents and Multi-Agent Systems (JAAMAS), and Machine Learning Journal (MLJ).
 
His research interests include planning and machine learning, particularly in multiagent systems. His doctoral thesis research contributed a flexible multiagent team structure and multiagent machine learning techniques for teams operating in real-time noisy environments in the presence of both teammates and adversaries. His long-term research goal is to create complete, robust, autonomous agents that can learn to interact with other intelligent agents in a wide range of complex, dynamic environments.
 
Peter is currently continuing his investigation of machine learning and multiagent learning at UT Austin. Application domains include robot soccer, autonomous bidding agents for auctions, and autonomous traffic management. Within the robot soccer domain, he is studying multiagent techniques in reinforcement learning, specifically temporal difference learning, for learning successful policies by a team of cooperating agents. In the context of auctions, he is investigating adaptive bidding policies that are applicable for simultaneous multi-round auctions involving interacting goods. In autonomic computing, he is focussing on automatic hardware configuration in response to changing workloads, and in autonomous intersection management he has developed a novel protocol by which autonomous vehicles can traverse intersections with 2 orders of magnitude less delay than is possible with traffic signals or stop signs.
 
He is a trustee of the international RoboCup Federation, was a co-chair of RoboCup-2001 at IJCAI-01, and was a Program Co-Chair of AAMAS 2006. He has developed teams of robot soccer agents that have won RoboCup championships in the simulation (1998, 1999, 2003, 2005) and in the small-wheeled robot (1997, 1998) leagues. He led tutorials on robot soccer at AAAI-99, Agents-99, and IJCAI-99. He has also developed agents that have won auction trading agents competitions (2000, 2001, 2003, 2005, 2006). He has served on various program committees and has co-chaired workshops on learning agents (at Agents-2000, Agents-2001, and the AAAI Spring Symposium in 2002) and on RoboCup (at RoboCup-2000).
 
Peter is the author of Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer and Intelligent Autonomous Robotics: A Robot Soccer Case Study (Synthesis Lectures on Artificial Intelligence and Machine Learning), coauthor of Autonomous Bidding Agents: Strategies and Lessons from the Trading Agent Competition, and coeditor of RoboCup 2000: Robot Soccer World Cup IV and Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems, as well as an author of many technical papers in conferences and journals.
 
Peter won best-paper awards at the RoboCup Symposium in 2007, at the Genetic and Evolutionary Computation Conference (GECCO) in 2006, and at the Agents-2001 conference. He was awarded the Allen Newell Medal for Excellence in Research in 1997. In 2003, he won a CAREER award from the National Science Foundation for his research on learning agents in dynamic, collaborative, and adversarial multiagent environments. In 2004, he was named an ONR Young Investigator for his research on machine learning on physical robots. Most recently, he was awarded the prestigious IJCAI 2007 Computers and Thought award.
 
He coauthored Instance-Based Action Models for Fast Action Planning, A Neural Network-Based Approach to Robot Motion Control, Negative Information and Line Observations for Monte Carlo Localization, Model-based Reinforcement Learning in a Complex Domain, Polynomial Regression with Automated Degree: A Function Approximator for Autonomous Agents, Transfer Learning and Intelligence: an Argument and Approach, and IFSA: Incremental Feature-Set Augmentation for Reinforcement Learning Task. Read the full list of his publications.
 
Watch his IJCAI 2007 Computers and Thought Award Talk. Read In This Soccer Match, Players Are Robotic But That’s the Goal. Read Is it Professor Stone or Coach Stone?