Multi-task reinforcement learning: a hierarchical Bayesian approach A Wilson, A Fern, S Ray, P Tadepalli Proceedings of the 24th international conference on Machine learning, 1015-1022, 2007 | 243 | 2007 |

Active learning with committees for text categorization R Liere, P Tadepalli AAAI/IAAI, 591-596, 1997 | 207 | 1997 |

Relational reinforcement learning: An overview P Tadepalli, R Givan, K Driessens Proceedings of the ICML-2004 workshop on relational reinforcement learning, 1-9, 2004 | 139 | 2004 |

Structured machine learning: the next ten years TG Dietterich, P Domingos, L Getoor, S Muggleton, P Tadepalli Machine Learning 73 (1), 3, 2008 | 129 | 2008 |

Dynamic preferences in multi-criteria reinforcement learning S Natarajan, P Tadepalli Proceedings of the 22nd international conference on Machine learning, 601-608, 2005 | 111 | 2005 |

Transfer in variable-reward hierarchical reinforcement learning N Mehta, S Natarajan, P Tadepalli, A Fern Machine Learning 73 (3), 289, 2008 | 105 | 2008 |

Automatic discovery and transfer of MAXQ hierarchies N Mehta, S Ray, P Tadepalli, T Dietterich Proceedings of the 25th international conference on Machine learning, 648-655, 2008 | 101 | 2008 |

Model-based average reward reinforcement learning P Tadepalli, DK Ok Artificial intelligence 100 (1-2), 177-224, 1998 | 100 | 1998 |

Lower bounding Klondike solitaire with Monte-Carlo planning R Bjarnason, A Fern, P Tadepalli Nineteenth International Conference on Automated Planning and Scheduling, 2009 | 96 | 2009 |

Maximizing the predictive value of production rules SM Weiss, RS Galen, PV Tadepalli Artificial Intelligence 45 (1-2), 47-71, 1990 | 95 | 1990 |

A bayesian approach for policy learning from trajectory preference queries A Wilson, A Fern, P Tadepalli Advances in neural information processing systems, 1133-1141, 2012 | 89 | 2012 |

Learning first-order probabilistic models with combining rules S Natarajan, P Tadepalli, TG Dietterich, A Fern Annals of Mathematics and Artificial Intelligence 54 (1-3), 223-256, 2008 | 82 | 2008 |

Lazy ExplanationBased Learning: A Solution to the Intractable Theory Problem. P Tadepalli IJCAI, 694-700, 1989 | 79 | 1989 |

Learning goal-decomposition rules using exercises C Reddy, P Tadepalli ICML, 278-286, 1997 | 69 | 1997 |

A Decision-Theoretic Model of Assistance. A Fern, S Natarajan, K Judah, P Tadepalli IJCAI, 1879-1884, 2007 | 66 | 2007 |

Imitation learning in relational domains: A functional-gradient boosting approach S Natarajan, S Joshi, P Tadepalli, K Kersting, J Shavlik Twenty-Second International Joint Conference on Artificial Intelligence, 2011 | 62 | 2011 |

Scaling up average reward reinforcement learning by approximating the domain models and the value function P Tadepalli, DK Ok ICML, 471-479, 1996 | 55 | 1996 |

HC-Search: A learning framework for search-based structured prediction JR Doppa, A Fern, P Tadepalli Journal of Artificial Intelligence Research 50, 369-407, 2014 | 53 | 2014 |

Using trajectory data to improve bayesian optimization for reinforcement learning A Wilson, A Fern, P Tadepalli The Journal of Machine Learning Research 15 (1), 253-282, 2014 | 51 | 2014 |

Learning first-order acyclic Horn programs from entailment C Reddy, P Tadepalli International Conference on Inductive Logic Programming, 23-37, 1998 | 51 | 1998 |