Transfer Learning
Traditional machine learning algorithms operate under the assumption that learning for each new task starts from scratch, thus disregarding any knowledge they may have gained while learning in previous domains. Naturally, if the domains encountered during learning are related, this tabula rasa approach would waste both data and computer time to develop hypotheses that could have been recovered by simply examining and possibly slightly modifying previously acquired knowledge. Moreover, the knowledge learned in earlier domains could capture generally valid rules that are not easily recoverable from small amounts of data, thus allowing the algorithm to achieve even higher levels of accuracy than it would if it starts from scratch.

The field of transfer learning, which has witnessed a great increase in popularity in recent years, addresses the problem of how to leverage previously acquired knowledge in order to improve the efficiency and accuracy of learning in a new domain that is in some way related to the original one. In particular, our current research is focused on developing transfer learning techniques for Markov Logic Networks (MLNs), a recently developed approach to statistical relational learning.

Our research in the area is currently sponsored by the Defense Advanced Research Projects Agency (DARPA) and managed by the Air Force Research Laboratory (AFRL) under contract FA8750-05-2-0283.

People
Erkin Bahceci Ph.D. Alumni erkin [at] cs utexas edu
Samuel Barrett Ph.D. Alumni sbarrett [at] cs utexas edu
W. Bradley Knox Ph.D. Alumni bradknox [at] mit edu
Elad Liebman Ph.D. Student eladlieb [at] cs utexas edu
Sanmit Narvekar Ph.D. Student sanmit [at] cs utexas edu
Jivko Sinapov Postdoctoral Alumni jsinapov [at] cs utexas edu
Peter Stone Faculty pstone [at] cs utexas edu
Publications
     [Expand to show all 49][Minimize]
Adversarial Imitation Learning from Video using a State Observer 2022
Haresh Karnan, Garrett Warnell, Faraz Torabi, and Peter Stone, In International Conference on Robotics and Automation, 2022, Philadelphia, Pennsylvania, May 2022.
VI-IKD: High-Speed Accurate Off-Road Navigation using Learned Visual-Inertial Inverse Kinodynamics 2022
Haresh Karnan, Kavan Sikand, Pranav Atreya, Sadegh Rabiee, Xuesu Xiao, Garrett Warnell, Peter Stone, and Joydeep Biswas, In International Conference on Intelligent Robots and Systems, 2022, Kyoto, Japan, October 2022.
VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation 2022
Haresh Karnan, Garrett Warnell, Xuesu Xiao, and Peter Stone, In International Conference on Robotics and Automation, 2022, Philadelphia, Pennsylvania, May 2022.
Zero-shot Video Moment Retrieval With Off-the-Shelf Models 2022
Anuj Diwan, Puyuan Peng, Raymond J. Mooney, In Workshop on Transfer Learning for Natural Language Processing at NeurIPS 2022, December 2022.
Grounded Action Transformation for Sim-to-Real Reinforcement Learning 2021
Josiah P.Hanna, Siddharth Desai, Haresh Karnan, Garrett Warnell, and Peter Stone, Special Issue on Reinforcement Learning for Real Life, Machine Learning, 2021 (2021).
Agents teaching agents: a survey on inter-agent transfer learning 2020
Felipe Leno Da Silva, Garrett Warnell, Anna Helena Reali Costa, and Peter Stone, Autonomous Agents and Multi-Agent Systems (2020).
An Imitation from Observation Approach to Transfer Learning with Dynamics Mismatch 2020
Siddarth Desai, Ishan Durugkar, Haresh Karnan, Garrett Warnell, Josiah Hanna, and Peter Stone, In Proceedings of the 34th International Conference on Neural Information Processing Systems (NeurIPS 2020), Virtual, December 2020.
Reinforced Grounded Action Transformation for Sim-to-Real Transfer 2020
Haresh Karnan, Siddharth Desai, Josiah P. Hanna, Garrett Warnell, and Peter Stone, In IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS 2020), October 2020.
Stochastic Grounded Action Transformation for Robot Learning in Simulation 2020
Siddharth Desai, Haresh Karnan, Josiah P. Hanna, Garrett Warnell, and Peter Stone, In IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS 2020), Las Vegas, NV, USA, October 2020.
Building Self-Play Curricula Online by Playing with Expert Agents in Adversarial Games 2019
Felipe Leno Da Silva, Anna Helena Reali Costa, and Peter Stone, In Proceedings of the 8th Brazilian Conference on Intelligent Systems (BRACIS), Salvador, Bahia, Brazil, October 2019.
Learning Curriculum Policies for Reinforcement Learning 2019
Sanmit Narvekar and Peter Stone, In Proceedings of the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Montreal, Canada, May 2019.
Automatic Curriculum Graph Generation for Reinforcement Learning Agents 2017
Maxwell Svetlik, Matteo Leonetti, Jivko Sinapov, Rishi Shah, Nick Walker, and Peter Stone, In Proceedings of the 31st AAAI Conference on Artificial Intelligence (AAAI), San Francisco, CA, February 2017.
Autonomous Task Sequencing for Customized Curriculum Design in Reinforcement Learning 2017
Sanmit Narvekar, Jivko Sinapov, and Peter Stone, In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, August 2017.
Making Friends on the Fly: Cooperating with New Teammates 2016
Samuel Barrett, Avi Rosenfeld, Sarit Kraus, and Peter Stone, Artificial Intelligence (2016).
Object-Model Transfer in the General Video Game Domain 2016
Alexander Braylan, Risto Miikkulainen, To Appear In Proceedings of the Twelfth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 2016.
Source Task Creation for Curriculum Learning 2016
Sanmit Narvekar, Jivko Sinapov, Matteo Leonetti, and Peter Stone, In Proceedings of the 15th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016), Singapore, May 2016.
Knowledge Transfer Using Latent Variable Models 2015
Ayan Acharya, PhD Thesis, Department of Electrical and Computer Engineering, The University of Texas at Austin.
Learning Inter-Task Transferability in the Absence of Target Task Samples 2015
Jivko Sinapov, Sanmit Narvekar, Matteo Leonetti, and Peter Stone, In Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Istanbul, Turkey, May 2015.
Active Multitask Learning Using Both Latent and Supervised Shared Topics 2014
Ayan Acharya, Raymond J. Mooney, and Joydeep Ghosh, In Proceedings of the 2014 SIAM International Conference on Data Mining (SDM14), Philadelphia, Pennsylvania, April 2014.
Using Both Latent and Supervised Shared Topics for Multitask Learning 2013
Ayan Acharya, Aditya Rawal, Raymond J. Mooney, Eduardo R. Hruschka, In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), pp. 369--384, Prague, Czech Republic, September 2013.
Learning Teammate Models for Ad Hoc Teamwork 2012
Samuel Barrett, Peter Stone, Sarit Kraus, and Avi Rosenfeld, In AAMAS Adaptive Learning Agents (ALA) Workshop, June 2012.
Adaptive Trading Agent Strategies Using Market Experience 2011
David Merrill Pardoe, No other information
An Introduction to Inter-task Transfer for Reinforcement Learning 2011
Matthew E. Taylor and Peter Stone, AI Magazine, Vol. 32, 1 (2011), pp. 15--34.
Boosting for Regression Transfer 2010
David Pardoe and Peter Stone, In Proceedings of the 27th International Conference on Machine Learning (ICML 2010), June 2010.
Transfer Learning for Reinforcement Learning on a Physical Robot 2010
Samuel Barrett, Matthew E. Taylor, and Peter Stone, In Ninth International Conference on Autonomous Agents and Multiagent Systems - Adaptive Learning Agents Workshop (AAMAS - ALA), May 2010.
Learning with Markov Logic Networks: Transfer Learning, Structure Learning, and an Application to Web Query Disambiguation 2009
Lilyana Mihalkova, PhD Thesis, Department of Computer Sciences, University of Texas at Austin. 176 pages.
Transfer Learning for Reinforcement Learning Domains: A Survey 2009
Matthew E. Taylor and Peter Stone, Journal of Machine Learning Research, Vol. 10, 1 (2009), pp. 1633-1685.
Transfer Learning from Minimal Target Data by Mapping across Relational Domains 2009
Lilyana Mihalkova and Raymond Mooney, In Proceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI-09), pp. 1163--1168, Pasadena, CA, July 2009.
Autonomous Transfer for Reinforcement Learning 2008
Matthew E. Taylor, Gregory Kuhlmann, and Peter Stone, In The Seventh International Joint Conference on Autonomous Agents and Multiagent Systems, May 2008.
Transfer Learning and Intelligence: an Argument and Approach 2008
Matthew E. Taylor, Gregory Kuhlmann, and Peter Stone, In Proceedings of the First Conference on Artificial General Intelligence, March 2008.
Transfer Learning by Mapping with Minimal Target Data 2008
Lilyana Mihalkova and Raymond J. Mooney, Proceedings of the AAAI-08 Workshop on Transfer Learning For Complex Tasks (2008).
Transfer of Evolved Pattern-Based Heuristics in Games 2008
Erkin Bahceci and Risto Miikkulainen, In IEEE Symposium On Computational Intelligence and Games (CIG 2008), pp. 220-227, Perth, Australia, December 2008.
Transferring Instances for Model-Based Reinforcement Learning 2008
Matthew E. Taylor, Nicholas K. Jong, and Peter Stone, In Machine Learning and Knowledge Discovery in Databases, Vol. 5212, pp. 488-505, September 2008.
Accelerating Search with Transferred Heuristics 2007
Matthew E. Taylor, Gregory Kuhlmann, and Peter Stone, In ICAPS-07 workshop on AI Planning and Learning, September 2007.
Cross-Domain Transfer for Reinforcement Learning 2007
Matthew E. Taylor and Peter Stone, In Proceedings of the Twenty-Fourth International Conference on Machine Learning, June 2007.
General Game Learning using Knowledge Transfer 2007
Bikramjit Banerjee and Peter Stone, In The 20th International Joint Conference on Artificial Intelligence, pp. 672-677, January 2007.
Graph-Based Domain Mapping for Transfer Learning in General Games 2007
Gregory Kuhlmann and Peter Stone, In Proceedings of the 18th European Conference on Machine Learning, September 2007.
Improving Learning of Markov Logic Networks using Transfer and Bottom-Up Induction 2007
Lilyana Mihalkova, Technical Report UT-AI-TR-07-341, Artificial Intelligence Lab, University of Texas at Austin.
Mapping and Revising Markov Logic Networks for Transfer Learning 2007
Lilyana Mihalkova, Tuyen N. Huynh, Raymond J. Mooney, In Proceedings of the Twenty-Second Conference on Artificial Intelligence (AAAI-07), pp. 608-614, Vancouver, BC, July 2007.
Representation Transfer for Reinforcement Learning 2007
Matthew E. Taylor and Peter Stone, In AAAI 2007 Fall Symposium on Computational Approaches to Representation Change during Learning and Development, November 2007.
Transfer Learning via Inter-Task Mappings for Temporal Difference Learning 2007
Matthew E. Taylor, Peter Stone, and Yaxin Liu, Journal of Machine Learning Research, Vol. 8, 1 (2007), pp. 2125-2167.
Transfer via Inter-Task Mappings in Policy Search Reinforcement Learning 2007
Matthew E. Taylor, Shimon Whiteson, and Peter Stone, In Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems, May 2007.
Transfer Learning with Markov Logic Networks 2006
Lilyana Mihalkova and Raymond Mooney, In Proceedings of the ICML-06 Workshop on Structural Knowledge Transfer for Machine Learning, Pittsburgh, PA, June 2006.
Value Function Transfer for General Game Playing 2006
Bikramjit Banerjee, Gregory Kuhlmann, and Peter Stone, In ICML workshop on Structural Knowledge Transfer for Machine Learning, June 2006.
Value-Function-Based Transfer for Reinforcement Learning Using Structure Mapping 2006
Yaxin Liu and Peter Stone, In Proceedings of the Twenty-First National Conference on Artificial Intelligence, pp. 415-20, July 2006.
Behavior Transfer for Value-Function-Based Reinforcement Learning 2005
Matthew E. Taylor and Peter Stone, In The Fourth International Joint Conference on Autonomous Agents and Multiagent Systems, Frank Dignum and Virginia Dignum and Sven Koenig and Sarit Kraus and Munindar P. Singh and Michael Woo...
Improving Action Selection in MDP's via Knowledge Transfer 2005
Alexander A. Sherstov and Peter Stone, In Proceedings of the Twentieth National Conference on Artificial Intelligence, July 2005.
State Abstraction Discovery from Irrelevant State Variables 2005
Nicholas K. Jong and Peter Stone, In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, pp. 752-757, August 2005.
Value Functions for RL-Based Behavior Transfer: A Comparative Study 2005
Matthew E. Taylor, Peter Stone, and Yaxin Liu, In Proceedings of the Twentieth National Conference on Artificial Intelligence, July 2005.
Projects
Teaching an Agent Manually via Evaluative Reinforcement (TAMER) 2008 - Present
Demos
Teaching an Agent Manually via Evaluative Reinforcement (TAMER)W. Bradley Knox and Peter Stone2009
Labs
Machine Learning Learning Agents