| Towards a Unified Theory of State Abstraction for MDPs. L Li, TJ Walsh, ML Littman ISAIM, 2006 | 318 | 2006 |
| Security considerations for voice over IP systems DR Kuhn, TJ Walsh, S Fries NIST special publication 800, 2005 | 318 | 2005 |
| Knows what it knows: a framework for self-aware learning L Li, ML Littman, TJ Walsh, AL Strehl Machine learning 82 (3), 399-443, 2011 | 256 | 2011 |
| T0901317 is a dual LXR/FXR agonist KA Houck, KM Borchert, CD Hepler, JS Thomas, KS Bramlett, LF Michael, ... Molecular genetics and metabolism 83 (1-2), 184-187, 2004 | 204 | 2004 |
| Towards Measuring Similarity in Description Logics. A Borgida, TJ Walsh, H Hirsh Description Logics 147, 2005 | 150 | 2005 |
| The founder mutation MSH2* 1906G→ C is an important cause of hereditary nonpolyposis colorectal cancer in the Ashkenazi Jewish population WD Foulkes, I Thiffault, SB Gruber, M Horwitz, N Hamel, C Lee, J Shia, ... The American Journal of Human Genetics 71 (6), 1395-1412, 2002 | 138 | 2002 |
| Challenges in securing voice over IP TJ Walsh, DR Kuhn IEEE Security & Privacy 3 (3), 44-49, 2005 | 128 | 2005 |
| Integrating sample-based planning and model-based reinforcement learning T Walsh, S Goschin, M Littman Proceedings of the AAAI Conference on Artificial Intelligence 24 (1), 2010 | 125 | 2010 |
| 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 TrendsŪ in Machine Learning 6 (4), 375-451, 2013 | 114 | 2013 |
| Exploring compact reinforcement-learning representations with linear regression TJ Walsh, I Szita, C Diuk, ML Littman arXiv preprint arXiv:1205.2606, 2012 | 101 | 2012 |
| Efficient learning of action schemas and web-service descriptions. TJ Walsh, ML Littman AAAI 8, 714-719, 2008 | 73 | 2008 |
| A natural product ligand of the oxysterol receptor, liver X receptor KS Bramlett, KA Houck, KM Borchert, MS Dowless, P Kulanthaivel, ... Journal of Pharmacology and Experimental Therapeutics 307 (1), 291-296, 2003 | 73 | 2003 |
| A Chemical Switch Regulates Fibrate Specificity for Peroxisome Proliferator-activated Receptor α (PPARα) VersusLiver X Receptor J Thomas, KS Bramlett, C Montrose, P Foxworthy, PI Eacho, D McCann, ... Journal of Biological Chemistry 278 (4), 2403-2410, 2003 | 63 | 2003 |
| Reinforcement learning with multi-fidelity simulators M Cutler, TJ Walsh, JP How 2014 IEEE International Conference on Robotics and Automation (ICRA), 3888-3895, 2014 | 58 | 2014 |
| Ligand-dependent coactivation of the human bile acid receptor FXR by the peroxisome proliferator-activated receptor γ coactivator-1α RS Savkur, JS Thomas, KS Bramlett, Y Gao, LF Michael, TP Burris Journal of Pharmacology and Experimental Therapeutics 312 (1), 170-178, 2005 | 52 | 2005 |
| Real-world reinforcement learning via multifidelity simulators M Cutler, TJ Walsh, JP How IEEE Transactions on Robotics 31 (3), 655-671, 2015 | 50 | 2015 |
| Bayesian nonparametric reward learning from demonstration B Michini, TJ Walsh, AA Agha-Mohammadi, JP How IEEE Transactions on Robotics 31 (2), 369-386, 2015 | 50 | 2015 |
| Transferring state abstractions between MDPs TJ Walsh, L Li, ML Littman ICML Workshop on Structural Knowledge Transfer for Machine Learning, 2006 | 50 | 2006 |
| Learning and planning in environments with delayed feedback TJ Walsh, A Nouri, L Li, ML Littman Autonomous Agents and Multi-Agent Systems 18 (1), 83, 2009 | 43 | 2009 |
| Sample efficient reinforcement learning with gaussian processes R Grande, T Walsh, J How International Conference on Machine Learning, 1332-1340, 2014 | 42 | 2014 |
