| 2015 | ICRA | Online Bayesian changepoint detection for articulated motion models. | Scott Niekum, Sarah Osentoski, Christopher G. Atkeson, Andrew G. Barto |
| 2014 | ICML | Active Learning of Parameterized Skills. | Bruno Castro da Silva, George Dimitri Konidaris, Andrew G. Barto |
| 2014 | ICRA | Learning parameterized motor skills on a humanoid robot. | Bruno Castro da Silva, Gianluca Baldassarre, George Dimitri Konidaris, Andrew G. Barto |
| 2012 | AAAI | Adaptive Step-Size for Online Temporal Difference Learning. | William Dabney, Andrew G. Barto |
| 2012 | AAAI | TD-DeltaPi: A Model-Free Algorithm for Efficient Exploration. | Bruno Castro da Silva, Andrew G. Barto |
| 2012 | ICML | Learning Parameterized Skills. | Bruno Castro da Silva, George Dimitri Konidaris, Andrew G. Barto |
| 2012 | IROS | Learning and generalization of complex tasks from unstructured demonstrations. | Scott Niekum, Sarah Osentoski, George Dimitri Konidaris, Andrew G. Barto |
| 2011 | AAAI | Autonomous Skill Acquisition on a Mobile Manipulator. | George Dimitri Konidaris, Scott Kuindersma, Roderic A. Grupen, Andrew G. Barto |
| 2011 | AAAI | Clustering via Dirichlet Process Mixture Models for Portable Skill Discovery. | Scott Niekum, Andrew G. Barto |
| 2011 | GECCO | Evolution of reward functions for reinforcement learning. | Scott Niekum, Lee Spector, Andrew G. Barto |
| 2011 | ICML | Conjugate Markov Decision Processes. | Philip S. Thomas, Andrew G. Barto |
| 2009 | IJCAI | Efficient Skill Learning using Abstraction Selection. | George Dimitri Konidaris, Andrew G. Barto |
| 2007 | AIED | Repairing Disengagement With Non-Invasive Interventions. | Ivon Arroyo, Kimberly Ferguson, Jeffrey Johns, Toby Dragon, Hasmik Meheranian, Don Fisher, Andrew G. Barto, Sridhar Mahadevan, Beverly Park Woolf |
| 2007 | IJCAI | Building Portable Options: Skill Transfer in Reinforcement Learning. | George Dimitri Konidaris, Andrew G. Barto |
| 2007 | IJCAI | Deictic Option Schemas. | Balaraman Ravindran, Andrew G. Barto, Vimal Mathew |
| 2007 | SECON | Adaptive Control of Duty Cycling in Energy-Harvesting Wireless Sensor Networks. | Christopher M. Vigorito, Deepak Ganesan, Andrew G. Barto |
| 2006 | AAAI | Decision Tree Methods for Finding Reusable MDP Homomorphisms. | Alicia P. Wolfe, Andrew G. Barto |
| 2006 | ICML | Autonomous shaping: knowledge transfer in reinforcement learning. | George Dimitri Konidaris, Andrew G. Barto |
| 2006 | ICML | An intrinsic reward mechanism for efficient exploration. | zgr Simsek, Andrew G. Barto |
| 2006 | ITS | Improving Intelligent Tutoring Systems: Using Expectation Maximization to Learn Student Skill Levels. | Kimberly Ferguson, Ivon Arroyo, Sridhar Mahadevan, Beverly Park Woolf, Andrew G. Barto |
| 2005 | ICML | A causal approach to hierarchical decomposition of factored MDPs. | Anders Jonsson, Andrew G. Barto |
| 2005 | ICML | Identifying useful subgoals in reinforcement learning by local graph partitioning. | zgr Simsek, Alicia P. Wolfe, Andrew G. Barto |
| 2004 | ICML | Using relative novelty to identify useful temporal abstractions in reinforcement learning. | zgr Simsek, Andrew G. Barto |
| 2004 | IJCNN | Reinforcement learning in the real world. | Andrew G. Barto |
| 2003 | ICML | Relativized Options: Choosing the Right Transformation. | Balaraman Ravindran, Andrew G. Barto |
| 2003 | IJCAI | SMDP Homomorphisms: An Algebraic Approach to Abstraction in Semi-Markov Decision Processes. | Balaraman Ravindran, Andrew G. Barto |
| 2002 | ICML | PolicyBlocks: An Algorithm for Creating Useful Macro-Actions in Reinforcement Learning. | Marc Pickett, Andrew G. Barto |
| 2001 | ICML | Automatic Discovery of Subgoals in Reinforcement Learning using Diverse Density. | Amy McGovern, Andrew G. Barto |
| 2001 | ICML | Lyapunov-Constrained Action Sets for Reinforcement Learning. | Theodore J. Perkins, Andrew G. Barto |
| 2001 | IJCAI | Heuristic Search in Infinite State Spaces Guided by Lyapunov Analysis. | Theodore J. Perkins, Andrew G. Barto |
| 2001 | IJCAI | Robot Weightlifting By Direct Policy Search. | Michael T. Rosenstein, Andrew G. Barto |
| 2000 | ICML | Machine Learning for Subproblem Selection. | Robert Moll, Theodore J. Perkins, Andrew G. Barto |
| 2000 | ICML | Combining Reinforcement Learning with a Local Control Algorithm. | Jette Randlv, Andrew G. Barto, Michael T. Rosenstein |
| 1997 | ICRA | Cerebellar learning for control of a two-link arm in muscle space. | Andrew H. Fagg, Nathan Sitkoff, Andrew G. Barto, James C. Houk |
| 1994 | ICRA | Learning Admittance Mappings for Force-Guided Assembly. | Vijaykumar Gullapalli, Andrew G. Barto, Roderic A. Grupen |
| 1992 | ICRA | Learning reactive admittance control. | Vijaykumar Gullapalli, Roderic A. Grupen, Andrew G. Barto |
| 1990 | AAAI | Explaining Temporal Differences to Create Useful Concepts for Evaluating States. | Richard C. Yee, Sharad Saxena, Paul E. Utgoff, Andrew G. Barto |
| 1990 | IJCNN | Cerebellar control of endpoint position-a simulation model. | T. Sinkjaer, C. H. Wu, Andrew G. Barto, James C. Houk |
| 1985 | IJCAI | Training and Tracking in Robotics. | Oliver G. Selfridge, Richard S. Sutton, Andrew G. Barto |