| Value function approximation in reinforcement learning using the Fourier basis G Konidaris, S Osentoski, P Thomas Proceedings of the Twenty-Fifth Conference on Artificial Intelligence, 380-385, 2011 | 269 | 2011 |
| Robot learning from demonstration by constructing skill trees G Konidaris, S Kuindersma, R Grupen, A Barto The International Journal of Robotics Research 31 (3), 360-375, 2012 | 239 | 2012 |
| Building Portable Options: Skill Transfer in Reinforcement Learning. GD Konidaris, AG Barto IJCAI 7, 895-900, 2007 | 235 | 2007 |
| Skill discovery in continuous reinforcement learning domains using skill chaining G Konidaris, A Barto Advances in Neural Information Processing Systems, 1015-1023, 2009 | 213 | 2009 |
| Autonomous shaping: Knowledge transfer in reinforcement learning G Konidaris, A Barto Proceedings of the 23rd international conference on Machine learning, 489-496, 2006 | 213 | 2006 |
| LQR-RRT*: Optimal sampling-based motion planning with automatically derived extension heuristics A Perez, R Platt, G Konidaris, L Kaelbling, T Lozano-Perez Robotics and Automation (ICRA), 2012 IEEE International Conference on, 2537-2542, 2012 | 177 | 2012 |
| Learning parameterized skills B Da Silva, G Konidaris, A Barto Proceedings of the Twenty Ninth International Conference on Machine Learning …, 2012 | 163 | 2012 |
| Learning and generalization of complex tasks from unstructured demonstrations S Niekum, S Osentoski, G Konidaris, AG Barto 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2012 | 156 | 2012 |
| Learning grounded finite-state representations from unstructured demonstrations S Niekum, S Osentoski, G Konidaris, S Chitta, B Marthi, AG Barto The International Journal of Robotics Research 34 (2), 131-157, 2015 | 138 | 2015 |
| Transfer in reinforcement learning via shared features G Konidaris, I Scheidwasser, AG Barto The Journal of Machine Learning Research 13 (1), 1333-1371, 2012 | 109 | 2012 |
| Constructing skill trees for reinforcement learning agents from demonstration trajectories G Konidaris, S Kuindersma, R Grupen, A Barto Advances in neural information processing systems, 1162-1170, 2010 | 92 | 2010 |
| Intrinsically motivated reinforcement learning: A promising framework for developmental robot learning A Stout, G Konidaris, A Barto MASSACHUSETTS UNIV AMHERST DEPT OF COMPUTER, 2005 | 86 | 2005 |
| Planning for decentralized control of multiple robots under uncertainty C Amato, G Konidaris, G Cruz, CA Maynor, JP How, LP Kaelbling 2015 IEEE International Conference on Robotics and Automation (ICRA), 1241-1248, 2015 | 83 | 2015 |
| Constructing Symbolic Representations for High-Level Planning. GD Konidaris, LP Kaelbling, T Lozano-Perez AAAI, 1932-1938, 2014 | 78 | 2014 |
| Efficient skill learning using abstraction selection G Konidaris, A Barto Twenty-First International Joint Conference on Artificial Intelligence, 2009 | 78 | 2009 |
| From skills to symbols: Learning symbolic representations for abstract high-level planning G Konidaris, LP Kaelbling, T Lozano-Perez Journal of Artificial Intelligence Research 61, 215-289, 2018 | 74 | 2018 |
| Policy search for multi-robot coordination under uncertainty C Amato, G Konidaris, A Anders, G Cruz, JP How, LP Kaelbling The International Journal of Robotics Research 35 (14), 1760-1778, 2016 | 70 | 2016 |
| Planning with macro-actions in decentralized POMDPs C Amato, GD Konidaris, LP Kaelbling Association for Computing Machinery (ACM), 2014 | 58 | 2014 |
| Autonomous skill acquisition on a mobile manipulator G Konidaris, S Kuindersma, R Grupen, A Barto Twenty-Fifth AAAI Conference on Artificial Intelligence, 2011 | 58 | 2011 |
| Reinforcement learning with parameterized actions W Masson, P Ranchod, G Konidaris Thirtieth AAAI Conference on Artificial Intelligence, 2016 | 56 | 2016 |
Andrew BartoUniversity of Massachusetts AmherstVerified email at cs.umass.edu
