Prasad Tadepalli

Professor
Computer Science Department
Oregon State University
Corvallis, OR 97331

Voice: (541) 737-5552
Fax: (541)-737-3014
e-mail: tadepall at cs dot orst dot edu
Office: 3069, Kelley Engineering Center
Postal Address: 1048, Kelley Engineering Center, Corvallis, OR 97331-3202, U.S.A.

Education

Teaching

Tutorials

• Reinforcement Learning: From Foundations to Advanced Topics , with Sridhar Mahadevan and Vivek Borkar, IJCAI 2007.
• Decision-Theoretic Planning and Learning in Relational Domains , with Alan Fern and Kristian Kersting, AAAI, 2008.

Research

• Workshop on Relational Reinforcement Learning
• Research Projects: Transfer Learning, Reinforcement Learning, Machine Reading, Relational Learning, Assistantship Learning, Structured Prediction, Learning in Planning
• Publications
• Applications of research: Real-Time Strategy Games, Air-space Management, Fire and Emergency Response, Product Delivery, Proactive Assistance, Card Games, Information Extraction

Useful Links

• Graduate Student Orientation at OSU Computer Science
• Machine Learning Reading Group
• Matrix cookbook
• Lisp lectures (Winter '06)
• Journal of AI Research
• The Harvard Guide to Happiness
• Graduate student resources maintained by Prof. Vasant Honavar
• What Every New Grad Student Should Know (Univ of Indiana)
• Department Dishonesty Policy
• Graduate Advising Guide
• Students with Disabilities Policy
• CSGSA home page

Current students

1. Janardhan Rao Doppa , Topic: Structured Prediction
2. Aaron Wilson , Topic: Bayesian Optimization for Reinforcement Learning
3. Walker Orr , Topic: Learning from Texts
4. Aswin Nadamuni Raghavan, Topic: Factored and Multiagent Planning
5. Mandana Hamidi, Topic: Imitation Learning of Hiererachical Policies

   Previous students

   1. Neville Mehta , PhD: Learning Hierarchies for Reinforcement Learning
   2. Scott Proper , PhD: Multi-agent Reinforcement Learning
   3. Ronny Bjarnason , PhD: Multi-level Rollout Reinforcement Learning
   4. Sriraam Natarajan , Ph.D.: Statistical Relational Learning
   5. Charles Parker, Ph.D: Structured Gradient Boosting
   6. Kiran Polavarapu, MS: Event and Sentiment Extraction in the Financial Domain
   7. Thierry Donneaugolencer, MS: Planning by Sparse Sampling in Partially Observable Domains
   8. Kim Mach, MS: Experimental Evaluation of Auto-exploratory Model-free Average-Reward Reinforcement Learning
   9. Nimish Dharawat, MS: Learning Tree Patterns for Information Extraction
   10. Sriraam Natarajan, MS: Multi-criterion Average-Reward Reinforcement Learning
   11. Sandeep Seri, MS : Hierarchical Average-reward Reinforcement Learning.
   12. Hong Tang, MS : Average-reward Reinforcement Learning for Product Delivery by Multiple Vehicles.
   13. Tom Amoth, PhD : Exact Learning of Tree Patterns.
   14. Ray Liere, PhD : Active learning with committees with applications to text categorization.
   15. Chandra Reddy, PhD : Learning Hierarchical Decomposition Rules for Planning: an Inductive Logic Programming Approach.
   16. DoKyeong Ok, PhD: A Study of Model-based Average Reward Reinforcement Learning.
   17. Michael Chisholm, MS: Learning Classification Rules by Radomized Iterative Local Search.
   18. Peter Drake, MS: Constructive Induction for Improved Learning of Boolean Functions
   19. Yenong Qi, MS: Local Search Methods for Job Shop Scheduling
   20. Silvana Roncagliolo, MS: Empirical Speedup Learning of Decomposition Rules for Planning
   21. Ramana Isukapalli, MS: Learning Macro-operators for Planning Using Simulators

   Vita

   ---

   Prasad Tadepalli, tadepall@cs.orst.edu