| Dyna-style planning with linear function approximation and prioritized sweeping RS Sutton, C Szepesvári, A Geramifard, MP Bowling arXiv preprint arXiv:1206.3285, 2012 | 175 | 2012 |
| A tutorial on linear function approximators for dynamic programming and reinforcement learning A Geramifard, TJ Walsh, S Tellex, G Chowdhary, N Roy, JP How Foundations and Trends® in Machine Learning 6 (4), 375-451, 2013 | 135 | 2013 |
| Decentralized control of partially observable Markov decision processes C Amato, G Chowdhary, A Geramifard, NK Üre, MJ Kochenderfer 52nd IEEE Conference on Decision and Control, 2398-2405, 2013 | 118 | 2013 |
| Incremental least-squares temporal difference learning A Geramifard, M Bowling, RS Sutton Proceedings of the National Conference on Artificial Intelligence 21 (1), 356, 2006 | 83 | 2006 |
| Online discovery of feature dependencies A Geramifard, F Doshi, J Redding, N Roy, JP How ICML, 2011 | 76 | 2011 |
| Cooperative mission planning for multi-UAV teams SS Ponda, LB Johnson, A Geramifard, JP How Handbook of unmanned aerial vehicles 2, 1447-1490, 2015 | 74 | 2015 |
| iLSTD: Eligibility traces and convergence analysis AGMBM Zinkevich, RS Sutton Advances in Neural Information Processing Systems 19: Proceedings of the …, 2007 | 58 | 2007 |
| On the design and use of a micro air vehicle to track and avoid adversaries R He, A Bachrach, M Achtelik, A Geramifard, D Gurdan, S Prentice, ... The International Journal of Robotics Research 29 (5), 529-546, 2010 | 53 | 2010 |
| RLPy: a value-function-based reinforcement learning framework for education and research. A Geramifard, C Dann, RH Klein, W Dabney, JP How J. Mach. Learn. Res. 16 (1), 1573-1578, 2015 | 47 | 2015 |
| UAV cooperative control with stochastic risk models A Geramifard, J Redding, N Roy, JP How Proceedings of the 2011 American Control Conference, 3393-3398, 2011 | 42 | 2011 |
| An intelligent cooperative control architecture J Redding, A Geramifard, A Undurti, HL Choi, JP How Proceedings of the 2010 American control conference, 57-62, 2010 | 36 | 2010 |
| Biased Cost Pathfinding. A Geramifard, P Chubak, V Bulitko AIIDE, 112-114, 2006 | 34 | 2006 |
| Reinforcement learning with misspecified model classes J Joseph, A Geramifard, JW Roberts, JP How, N Roy 2013 IEEE International Conference on Robotics and Automation, 939-946, 2013 | 33 | 2013 |
| Adaptive planning for Markov decision processes with uncertain transition models via incremental feature dependency discovery NK Ure, A Geramifard, G Chowdhary, JP How Joint European conference on machine learning and knowledge discovery in …, 2012 | 31 | 2012 |
| Customized movie trailers A Geramifard US Patent App. 14/105,428, 2015 | 27 | 2015 |
| Intelligent cooperative control architecture: a framework for performance improvement using safe learning A Geramifard, J Redding, JP How Journal of Intelligent & Robotic Systems 72 (1), 83-103, 2013 | 27 | 2013 |
| Learning robust dialog policies in noisy environments M Fazel-Zarandi, SW Li, J Cao, J Casale, P Henderson, D Whitney, ... arXiv preprint arXiv:1712.04034, 2017 | 20 | 2017 |
| RLPy: The Reinforcement Learning Library for Education and Research A Geramifard, RH Klein, P Jonathan | 18 | 2013 |
| Practical reinforcement learning using representation learning and safe exploration for large scale Markov decision processes A Geramifard Massachusetts Institute of Technology, 2012 | 17 | 2012 |
| Situated and interactive multimodal conversations S Moon, S Kottur, PA Crook, A De, S Poddar, T Levin, D Whitney, ... arXiv preprint arXiv:2006.01460, 2020 | 14 | 2020 |
Jonathan P. HowRichard C. Maclaurin Professor of Aerospace Engineering, Massachusetts Institute of TechnologyVerified email at mit.edu
