Search Machine Learning Repository:
All publications by Andrew G. Barto
authors venues years



Learning Parameterized Skills
Bruno D. Silva, George Konidaris and Andrew G. Barto
Proceedings of the 29th International Conference on Machine Learning (ICML-12), 2012


Clustering via Dirichlet Process Mixture Models for Portable Skill Discovery
Scott Niekum and Andrew G. Barto
Advances in Neural Information Processing Systems 24, 2011


Conjugate Markov Decision Processes
Philip S. Thomas and Andrew G. Barto
Proceedings of the 28th International Conference on Machine Learning (ICML-11), 2011


An intrinsic reward mechanism for efficient exploration
Özgür Simsek and Andrew G. Barto
Proceedings of the 23th International Conference on Machine Learning (ICML-06), 2006


Autonomous shaping: knowledge transfer in reinforcement learning
George Konidaris and Andrew G. Barto
Proceedings of the 23th International Conference on Machine Learning (ICML-06), 2006


Causal Graph Based Decomposition of Factored MDPs
Anders Jonsson and Andrew G. Barto
Journal of Machine Learning Research, 2006


Identifying useful subgoals in reinforcement learning by local graph partitioning
Özgür Simsek, Alicia P. Wolfe and Andrew G. Barto
Proceedings of the 22nd International Conference on Machine Learning (ICML-05), 2005


A causal approach to hierarchical decomposition of factored MDPs
Anders Jonsson and Andrew G. Barto
Proceedings of the 22nd International Conference on Machine Learning (ICML-05), 2005


Using relative novelty to identify useful temporal abstractions in reinforcement learning
Özgür Simsek and Andrew G. Barto
Proceedings of the 21st International Conference on Machine Learning (ICML-04), 2004


Intrinsically Motivated Reinforcement Learning
Nuttapong Chentanez, Andrew G. Barto and Satinder P. Singh
Advances in Neural Information Processing Systems 17, 2004


Relativized Options: Choosing the Right Transformation
Balaraman Ravindran and Andrew G. Barto
Proceedings of the 20th International Conference on Machine Learning (ICML-03), 2003


Lyapunov Design for Safe Reinforcement Learning
Theodore J. Perkins and Andrew G. Barto
Journal of Machine Learning Research, 2002


The Emergence of Multiple Movement Units in the Presence of Noise and Feedback Delay
Michael Kositsky and Andrew G. Barto
Advances in Neural Information Processing Systems 14, 2001