Agent Modeling in Multiagent Systems
In multiagent systems, when the other agents are initially unknown, it can be useful to build a model of their behaviors so as to predict their future actions. This can apply to teammates, opponents, and agents with unrelated goals that act in the same environment.
People
Tsz-Chiu Au Alumni chiu@cs.utexas.edu
Peter Stone Professor pstone@cs.utexas.edu
Publications
Learning Teammate Models for Ad Hoc Teamwork 2012
Samuel Barrett and Peter Stone and Sarit Kraus and Avi Rosenfeld
Empirical Evaluation of Ad Hoc Teamwork in the Pursuit Domain 2011
Samuel Barrett and Peter Stone and Sarit Kraus
Structure Learning in Ergodic Factored MDPs without Knowledge of the Transition Function's In-Degree 2011
Doran Chakraborty and Peter Stone
Convergence, Targeted Optimality and Safety in Multiagent Learning 2010
Doran Chakraborty and Peter Stone
Online Model Learning in Adversarial Markov Decision Processes (Extended Abstract) 2010
Doran Chakraborty and Peter Stone
Leading a Best-Response Teammate in an Ad Hoc Team 2009
Peter Stone and Gal A. Kaminka and Jeffrey S. Rosenschein
Know Thine Enemy: A Champion RoboCup Coach Agent 2006
Gregory Kuhlmann and William B. Knox and Peter Stone
The UT Austin Villa 2003 Champion Simulator Coach: A Machine Learning Approach 2005
Gregory Kuhlmann and Peter Stone and Justin Lallinger
Defining and Using Ideal Teammate and Opponent Models 2000
Peter Stone and Patrick Riley and Manuela Veloso
Labs
Learning Agents