| Safe exploration in markov decision processes TM Moldovan, P Abbeel arXiv preprint arXiv:1205.4810, 2012 | 412 | 2012 |
| Scaling the Mobile Millennium system in the cloud T Hunter, T Moldovan, M Zaharia, S Merzgui, J Ma, MJ Franklin, P Abbeel, ... Proceedings of the 2nd ACM Symposium on Cloud Computing, 1-8, 2011 | 85 | 2011 |
| Risk aversion in Markov decision processes via near optimal Chernoff bounds T Moldovan, P Abbeel Advances in neural information processing systems 25, 2012 | 60 | 2012 |
| Model-based reinforcement learning with parametrized physical models and optimism-driven exploration C Xie, S Patil, T Moldovan, S Levine, P Abbeel 2016 IEEE international conference on robotics and automation (ICRA), 504-511, 2016 | 56 | 2016 |
| Optimism-driven exploration for nonlinear systems TM Moldovan, S Levine, MI Jordan, P Abbeel 2015 IEEE International Conference on Robotics and Automation (ICRA), 3239-3246, 2015 | 48 | 2015 |
| Denoising archival films using a learned Bayesian model TM Moldovan, S Roth, MJ Black 2006 International Conference on Image Processing, 2641-2644, 2006 | 25 | 2006 |
| Safety, risk awareness and exploration in reinforcement learning TM Moldovan, P Abbeel, M Jordan, F Borrelli University of California, Berkeley, USA, 2014 | 6 | 2014 |
| Dirichlet Process reinforcement learning TM Moldovan, MI Jordan, P Abbeel Reinforcement Learning and Decision Making Meeting, 2013 | 1 | 2013 |
| Csaba Szepesvári University of Alberta A Geramifard, A Lazaric, A Farahmand, AD Salles, AMH Barreto, ... | | 2012 |
| Near Optimal Chernoff Bounds for Markov Decision Processes TM Moldovan University of California, Berkeley, 2012 | | 2012 |
