Simulated Robot Soccer
RoboCup soccer also has a couple of simulation platforms that are very useful for studying full-team interactions and multiagent learning. The keepaway domain is a subtask that we have defined and that has become a standard reinforcement learning benchmark.
People
Peter Stone Professor pstone@cs.utexas.edu
Publications (45)
Humanoid Robots Learning to Walk Faster: From the Real World to Simulation and Back 2013
Alon Farchy and Samuel Barrett and Patrick MacAlpine and Peter Stone
Positioning to Win: A Dynamic Role Assignment and Formation Positioning System 2013
Patrick MacAlpine and Francisco Barrera and Peter Stone
Simultaneous Learning and Reshaping of an Approximated Optimization Task 2013
Patrick MacAlpine and Elad Liebman and Peter Stone
{UT} {A}ustin {V}illa: {R}obo{C}up 2012 3{D} Simulation League Champion 2013
Patrick MacAlpine and Nick Collins and Adrian Lopez-Mobilia and Peter Stone
Design and Optimization of an Omnidirectional Humanoid Walk: A Winning Approach at the {R}obo{C}up 2011 3{D} Simulation Competition 2012
Patrick MacAlpine and Samuel Barrett and Daniel Urieli and Victor Vu and Peter Stone
Using Dynamic Rewards to Learn a Fully Holonomic Bipedal Walk 2012
Patrick MacAlpine and Peter Stone
{UT} {A}ustin {V}illa 2011: A Champion Agent in the {R}obo{C}up 3{D} Soccer Simulation Competition 2012
Patrick MacAlpine and Daniel Urieli and Samuel Barrett and Shivaram Kalyanakrishnan and Francisco Barrera and Adrian Lopez-Mobilia and Nicolae Stiurca and Victor Vu and Peter Stone
{W}right {E}agle and {UT} {A}ustin {V}illa: {R}obo{C}up 2011 Simulation League Champions 2012
Aijun Bai and Xiaoping Chen and Patrick MacAlpine and Daniel Urieli and Samuel Barrett and Peter Stone
On Optimizing Interdependent Skills: A Case Study in Simulated 3D Humanoid Robot Soccer 2011
Daniel Urieli and Patrick MacAlpine and Shivaram Kalyanakrishnan and Yinon Bentor and Peter Stone
{UT} {A}ustin {V}illa 2011 3{D} {S}imulation {T}eam Report 2011
Patrick MacAlpine and Daniel Urieli and Samuel Barrett and Shivaram Kalyanakrishnan and Francisco Barrera and Adrian Lopez-Mobilia and Nicolae Stiurca and Victor Vu and Peter Stone
Learning in Fractured Problems for Constructive Neural Network Algorithms 2009
Nate Kohl
The UT Austin Villa 3D Simulation Soccer Team 2008 2009
Shivaram Kalyanakrishnan and Yinon Bentor 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
Model-based Reinforcement Learning in a Complex Domain 2008
Shivaram Kalyanakrishnan and Peter Stone and Yaxin Liu
Batch Reinforcement Learning in a Complex Domain 2007
Shivaram Kalyanakrishnan and Peter Stone
Empirical Studies in Action Selection for Reinforcement Learning 2007
Shimon Whiteson and Matthew E. Taylor and Peter Stone
Half Field Offense in RoboCup Soccer: A Multiagent Reinforcement Learning Case Study 2007
Shivaram Kalyanakrishnan and Yaxin Liu and Peter Stone
The UT Austin Villa 3D Simulation Soccer Team 2007 2007
Shivaram Kalyanakrishnan and Peter Stone
Comparing Evolutionary and Temporal Difference Methods for Reinforcement Learning 2006
Matthew Taylor and Shimon Whiteson and Peter Stone
Keepaway Soccer: From Machine Learning Testbed to Benchmark 2006
Peter Stone and Gregory Kuhlmann and Matthew E. Taylor and Yaxin Liu
Know Thine Enemy: A Champion RoboCup Coach Agent 2006
Gregory Kuhlmann and William B. Knox and Peter Stone
Evolving Keepaway Soccer Players through Task Decomposition 2005
Shimon Whiteson and Nate Kohl and Risto Miikkulainen and Peter Stone
Reinforcement Learning for RoboCup-Soccer Keepaway 2005
Peter Stone and Richard S. Sutton and Gregory Kuhlmann
The UT Austin Villa 2003 Champion Simulator Coach: A Machine Learning Approach 2005
Gregory Kuhlmann and Peter Stone and Justin Lallinger
Guiding a Reinforcement Learner with Natural Language Advice: Initial Results in RoboCup Soccer 2004
Gregory Kuhlmann, Peter Stone, Raymond J. Mooney, and Jude W. Shavlik
Concurrent Layered Learning 2003
Shimon Whiteson and Peter Stone
The RoboCup Soccer Server and CMUnited Clients: Implemented Infrastructure for MAS Research 2003
Itsuki Noda and Peter Stone
ATTUnited-2001: Using Heterogeneous Players 2002
Peter Stone
An Architecture for Action Selection in Robotic Soccer 2001
Peter Stone and David McAllester
ATT-CMUnited-2000: Third Place Finisher in the RoboCup-2000 Simulator League 2001
Patrick Riley and Peter Stone and David McAllester and Manuela Veloso
Keeping the Ball from CMUnited-99 2001
David McAllester and Peter Stone
Layered Disclosure: Revealing Agents' Internals 2001
Patrick Riley and Peter Stone and Manuela Veloso
Defining and Using Ideal Teammate and Opponent Models 2000
Peter Stone and Patrick Riley and Manuela Veloso
The CMUnited-99 Champion Simulator Team 2000
Peter Stone and Patrick Riley and Manuela Veloso
Anticipation as a Key for Collaboration in a Team of Agents: A Case Study in Robotic Soccer 1999
Manuela Veloso and Peter Stone and Michael Bowling
Task Decomposition, Dynamic Role Assignment, and Low-Bandwidth Communication for Real-Time Strategic Teamwork 1999
Peter Stone and Manuela Veloso
Team-Partitioned, Opaque-Transition Reinforcement Learning 1999
Peter Stone and Manuela Veloso
The CMUnited-98 Champion Simulator Team 1999
Peter Stone and Manuela Veloso and Patrick Riley
A Layered Approach to Learning Client Behaviors in the RoboCup Soccer Server 1998
Peter Stone and Manuela Veloso
The CMUnited-97 Simulator Team 1998
Peter Stone and Manuela Veloso
Towards Collaborative and Adversarial Learning: A Case Study in Robotic Soccer 1998
Peter Stone and Manuela Veloso
Using Decision Tree Confidence Factors for Multiagent Control 1998
Peter Stone and Manuela Veloso
The RoboCup Synthetic Agent Challenge 97 1997
Hiroaki Kitano and Milind Tambe and Peter Stone and Manuela Veloso and Silvia Coradeschi and Eiichi Osawa and Hitoshi Matsubara and Itsuki Noda and Minoru Asada
Beating a Defender in Robotic Soccer: Memory-Based Learning of a Continuous Function 1996
Peter Stone and Manuela Veloso
Predictive Memory for an Inaccessible Environment 1996
Mike Bowling and Peter Stone and Manuela Veloso
Labs
Learning Agents