Prasad Tadepalli

Professor

Computer Science

Web Page:

http://eecs.oregonstate.edu/~tadepall/

Education:

PhD, Computer Science, Rutgers University, U.S., 1990;
MTech, Computer Science, Indian Institute of Technology, Madras, India, 1981;
BTech, Electrical Engineering, Regional Engineering College, Warangal, India, 1979.

Biography:

Prasad Tadepalli has an M. Tech in Computer Science from Indian Institute of Technology, Madras, India and a Ph.D. from Rutgers University, New Brunswick. He joined Oregon State University, Corvallis, as an assistant professor in 1989. He is now a professor in the School of Electrical Engineering and Computer Science of Oregon State University.

He co-authored over a hundred papers in Artificial Intelligence and Machine Learning in various journals, conferences, and workshops. He organized many workshops and tutorials and co-chaired the international conference on inductive logic programming in 2007. He was a member of many conference program committees and is currently an action editor for the Journal of Artificial Intelligence Research, and the Machine Learning journal.

Research group:

AI - Machine Learning - Algorithms

Research Interests:

Research Areas

Artificial Intelligence, Machine Learning, Automated Planning and Reasoning, Natural Language Processing.

Research Description

My main research interest is to understand learning and thinking by simulating them in computers. My work ranges from theoretical analyses of learning problems and algorithms to their implementation, evaluation, and application to real-world problems.

One of my research thrusts is to learn to act intelligently by building models of actions, planning or reasoning with them, executing the plans, and learning better models and ways to plan with them. There are several interesting questions here such as how to model only what is needed, how to account for errors in the models, how best to combine knowledge and search in planning, how to learn from observation as well as practice, how to exploit hierarchies in planning and learning, and how to transfer knowledge from one domain to a related domain.

Another research thrust is to learn in structured contexts such as natural language processing where the examples have rich internal structure, and are noisy, incomplete, biased, and highly interconnected.

The interesting issues here include learning in expressive representations, learning multiple related concepts simultaneously, constraining learning by explicit prior knowledge, accounting for bias and incompleteness in the data, and integrated learning and reasoning.

Applications of Research

The applications of research include fire and medical emergency response, learning and training systems for expert tasks, intelligent assistants for disabled and elderly, and personalized medicine.

Teaching:

CS 517 THEORY OF COMPUTATION

Publications

2011

Fern, A., R. Khardon, and P. Tadepalli, "The first learning track of the international planning competition", Machine Learning, vol. 84, issue 1-2, pp. 81 - 107, 07/2011. Abstract

Sorower, M. S., T. G. Dietterich, J. R. Doppa, P. Tadepalli, and X. Fern, "Learning Rules from Incomplete Examples via a Probabilistic Mention Model", IJCAI 2011 Workshop on Learning by Reading and its Applications in Intelligent Question-Answering, Barcelona, Catalonia, Spain, 07/2011. Abstract

Doppa, J. R., M. NasrEsfahani, M. S. Sorower, J. Irvine, T. G. Dietterich, X. Fern, and P. Tadepalli, "Learning Rules from Incomplete Examples via Observation Models", IJCAI 2011 Workshop on Learning by Reading and its Applications in Intelligent Question-Answering, Barcelona, Catalonia, Spain, 07/2011. Abstract

2010

Fern, A., and P. Tadepalli, "A Computational Decision Theory for Interactive Assistants", Advances in Neural Information Processing Systems (NIPS-2010), Vancouver, B.C., Canada, pp. 577–585, 12/2010. Abstract

Wilson, A., A. Fern, and P. Tadepalli, "Incorporating domain models into Bayesian optimization for RL", Proceedings of the 2010 European Conference on Machine Learning, Casa Convalescència, Barcelona, Catalonia, Spain, Springer-Verlag, pp. 467–482, 09/2010. Abstract

Wilson, A., A. Fern, and P. Tadepalli, "Bayesian Policy Search for Multi-Agent Role Discovery", AAAI Conference on Artificial Intelligence (AAAI-2010), Atlanta, Georgia, pp. 624-629, 07/2010. Abstract

Fern, A., and P. Tadepalli, "A Computational Decision Theory for Interactive Assistants", AAAI Workshop on Interactive Decision Theory and Game Theory, Atlanta, GA, 07/2010. Abstract

Wilson, A., A. Fern, and P. Tadepalli, "Bayesian Role Discovery for Multi-Agent Reinforcement Learning (extended abstract)", International Conference on Autonomous Agents and Multiagent Systems (AAMAS-2010), Toronto Canada, 05/2010. Abstract

2009

Bjarnason, R., A. Fern, and P. Tadepalli, "Lower Bounding Klondike Solitaire with Monte-Carlo Planning", International Conference on Automated Planning and Scheduling (ICAPS-2009), Thessaloniki, Greece, 09/2009. Abstract

Zhang, X., S. Yoon, P. DiBona, D. S. Appling, L. Ding, J. R. Doppa, D. Green, J. K. Guo, U. Kuter, G. Levine, et al., "An Ensemble Learning and Problem-Solving Architecture for Airspace Management", Proceedings of Twenty-First Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-09), Pasadena, CA, pp. 203-210, 07/2009. Abstract

Bjarnason, R., P. Tadepalli, A. Fern, and C. Niedner, "Simulation-based Optimization of Resource Placement and Emergency Response.", IAAI, Pasadena, CA, Innovative Applications of Artificial Intelligence (IAAI-2009), 07/2009. Abstract

Dietterich, T. G., A. Fern, J. Irvine, M. Slater, P. Tadepalli, M. Gervasio, C. Ellwood, B. Jarrold, O. Brdiczka, and J. Blythe, "User Initiated Learning for Adaptive Interfaces Abstract", IJCAI2009 Workshop on Intelligence and Interaction, Pasadena, CA, 07/2009. Abstract

2008

Mehta, N., S. Natarajan, P. Tadepalli, and A. Fern, "Transfer in variable-reward hierarchical reinforcement learning", Machine Learning, vol. 73, issue 3, pp. 289 - 312, 12/2008. Abstract

Natarajan, S., P. Tadepalli, T. G. Dietterich, and A. Fern, "Learning first-order probabilistic models with combining rules", Annals of Mathematics and Artificial Intelligence, vol. 54, issue 1-3, pp. 223 - 256, 11/2008. Abstract

Dietterich, T. G., P. Domingos, L. Getoor, S. Muggleton, and P. Tadepalli, "Structured machine learning: the next ten years", Machine Learning, vol. 73, issue 1, pp. 3 - 23, 10/2008. Abstract

Natarajan, S., H. H. Bui, P. Tadepalli, K. Kersting, and W. - K. Wong, "Logical Hierarchical Hidden Markov Models for Modeling User Activities", Proceedings of the Eighteenth International Conference on Inductive Logic Programming, vol. 5194, Prague, Czech Republic, Springer Berlin Heidelberg, pp. 192 - 209, 09/2008. Abstract

Mehta, N., S. Ray, P. Tadepalli, and T. G. Dietterich, "Automatic discovery and transfer of MAXQ hierarchies", Proceedings of the 25th International Conference on Machine learning - ICML '08, Helsinki, Finland, ACM Press, pp. 648 - 655, 07/2008. Abstract

Wilson, A., A. Fern, S. Ray, and P. Tadepalli, "Learning and Transferring Roles in Multi-Agent Reinforcement Learning", AAAI-08 Workshop on Transfer Learning for Complex Tasks, Chicago, IL, 07/2008. Abstract

Natarajan, S., P. Tadepalli, and A. Fern, "A relational hierarchical model for decision-theoretic assistance", International Conference on Inductive Logic Programming (ILP-2007), Corvallis, OR, Springer-Verlag, pp. 175–190, 06/2007, 2008. Abstract

2007

Mills-Price, C., W. - K. Wong, P. Tadepalli, and E. W. Dereszynski, "Bi-level Optimization for Learning Cost Functions from Demonstration", 2007 AAAI Workshop on Acquiring Planning Knowledge via Demonstration, Vancouver, BC, pp. 18-20, 07/2007. Abstract

Parker, C., P. Tadepalli, W. - K. Wong, T. G. Dietterich, and A. Fern, "Learning From Demonstrations via Structured Prediction", 2007 AAAI Workshop on Acquiring Planning Knowledge via Demonstration, Vancouver, BC, pp. 34-40, 07/2007. Abstract

Parker, C., A. Fern, and P. Tadepalli, "Learning for efficient retrieval of structured data with noisy queries", Proceedings of the 24th international conference on Machine learning - ICML '07, Corvalis, Oregon, ACM Press, pp. 729 - 736, 06/2007. Abstract

Wilson, A., A. Fern, S. Ray, and P. Tadepalli, "Multi-task reinforcement learning", Proceedings of the 24th international conference on Machine learning - ICML '07, Corvalis, Oregon, ACM Press, pp. 1015 - 1022, 06/2007. Abstract

Bjarnason, R., P. Tadepalli, and A. Fern, "Searching Solitaire in Real Time.", International Computer Games Association Journal, vol. 30, issue 3, 06/2007. Abstract

Fern, A., S. Natarajan, K. Judah, and P. Tadepalli, "A decision-theoretic model of assistance", International Joint Conference on Artificial Intelligence (IJCAI-2007), Hyderabad, India, 01/2007. Abstract

School of Electrical Engineering & Computer Science