Matthew Hausknecht
Neural Networks Lab: Formerly affiliated Collaborator
Learning Agents Lab: Ph.D. Alumni
Matthew's research focuses on understanding the principles of cerebellar learning and its applications to pattern recognition, supervised learning, and control. Additionally, he investigates general purpose learning by developing general game playing agents for Atari 2600 video games. In his spare time Matthew is an avid rock climber.
Homepage:
http://www.cs.utexas.edu/~mhauskn
Publications
     [Expand to show all 16][Minimize]
Deep Imitation Learning for Parameterized Action Spaces 2016
Matthew Hausknecht, Yilun Chen, and Peter Stone, In AAMAS Adaptive Learning Agents (ALA) Workshop, Singapore, May 2016.
Deep Reinforcement Learning in Parameterized Action Space 2016
Matthew Hausknecht and Peter Stone, In Proceedings of the International Conference on Learning Representations (ICLR), San Juan, Puerto Rico, May 2016.
Grounded Semantic Networks for Learning Shared Communication Protocols 2016
Matthew Hausknecht and Peter Stone, In Deep Reinforcement Learning, NIPS Workshop, Barcelona, Spain, December 2016.
Half Field Offense: An Environment for Multiagent Learning and Ad Hoc Teamwork 2016
Matthew Hausknecht, Prannoy Mupparaju, Sandeep Subramanian, Shivaram Kalyanakrishnan, and Peter Stone, In AAMAS Adaptive Learning Agents (ALA) Workshop, Singapore, May 2016.
Machine Learning Capabilities of a Simulated Cerebellum 2016
Matthew Hausknecht, Wen-Ke Li, Michael Mauk, and Peter Stone, IEEE Transactions on Neural Networks and Learning Systems (2016).
On-Policy vs. Off-Policy Updates for Deep Reinforcement Learning 2016
Matthew Hausknecht and Peter Stone, In Deep Reinforcement Learning: Frontiers and Challenges, IJCAI Workshop, New York, July 2016.
Deep Recurrent Q-Learning for Partially Observable MDPs 2015
Matthew Hausknecht and Peter Stone, In AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents (AAAI-SDMIA15), Arlington, Virginia, USA, November 2015.
The Impact of Determinism on Learning Atari 2600 Games 2015
Matthew Hausknecht and Peter Stone, In AAAI Workshop on Learning for General Competency in Video Games, Austin, Texas, USA, January 2015.
A Neuroevolution Approach to General Atari Game Playing 2013
Matthew Hausknecht, Joel Lehman, Risto Miikkulainen, and Peter Stone, IEEE Transactions on Computational Intelligence and AI in Games (2013).
HyperNEAT-GGP: A HyperNEAT-based Atari General Game Player 2012
Matthew Hausknecht, Piyush Khandelwal, Risto Miikkulainen, Peter Stone, In Genetic and Evolutionary Computation Conference (GECCO) 2012 2012.
Using a million cell simulation of the cerebellum: Network scaling and task generality 2012
Wen-Ke Li, Matthew J. Hausknecht, Peter Stone, and Michael D. Mauk, Neural Networks (2012).
Austin Villa 2010 Standard Platform Team Report 2011
Samuel Barrett, Katie Genter, Matthew Hausknecht, Todd Hester, Piyush Khandelwal, Juhyun Lee, Michael Quinlan, Aibo Tian, Peter Stone, and Mohan Sridharan, Technical Report, Department of Computer Science, The University of Texas at Austin. Tech Report UT-AI-TR-11-01.
Autonomous Intersection Management: Multi-Intersection Optimization 2011
Matthew Hausknecht, Tsz-Chiu Au, and Peter Stone, In Proceedings of IROS 2011-IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), September 2011.
Dynamic Lane Reversal in Traffic Management 2011
Matthew Hausknecht, Tsz-Chiu Au, Peter Stone, David Fajardo, and Travis Waller, In Proceedings of IEEE Intelligent Transportation Systems Conference (ITSC), October 2011.
Learning Powerful Kicks on the Aibo ERS-7: The Quest for a Striker 2010
Matthew Hausknecht and Peter Stone, In Robocup International Symposium 2010.
Vision Calibration and Processing on a Humanoid Soccer Robot 2010
Piyush Khandelwal, Matthew Hausknecht, Juhyun Lee, Aibo Tian, and Peter Stone, In The Fifth Workshop on Humanoid Soccer Robots at Humanoids 2010, Nashville, TN 2010.
Areas of Interest
Deep Learning Evolutionary Computation Game Playing Neuroevolution
Demos
A Neuroevolution Approach to General Atari Game PlayingMatthew Hausknecht2013
Labs
Formerly affiliated with Neural Networks Formerly affiliated with Learning Agents