* Scott Proper

PhD Student
Computer Science Department
Oregon State University
Corvallis, OR 97331

Voice: (541) 754-7952
e-mail: proper@eecs.oregonstate.edu
Postal Address: 346 NW 15th Apt. C, Corvallis, OR 97330

Research Accomplishments (PDF)
Research Statement/Goals (PDF)
Curriculum Vitae (PDF) (HTML)

Research Interests

I am greatly interested in problems involving machine learning, in particular difficulties involved in scaling reinforcement learning to solve complex domains. I am inspired and challenged by multiagent systems in particular: for example, problems in representing a value function over many states, problems of action selection by multiple agents, and of coordinating actions in multiagent domains. There are several broad approaches to these problems I have examined so far, including relational reinforcement learning, heirarchical reinforcement learning, function approximation, and coordination graphs.

Thesis

  • Proper, S., Scaling Multiagent Reinforcement Learning,
    PDF Version 1.2

    Publications

  • Proper, S., Tadepalli, P., Tang, H., Logendran, R., A Reinforcement Learning Approach for Product Delivery by Multiple Vehicles,
    for IIE/IERC 2003: Institute of Industrial Engineers/Industrial Engineering Research Conference.
    PDF PostScript

  • Proper, S., Tadepalli, P., Scaling Average-reward Reinforcement Learning for Product Delivery,
    for AAAI Real Life Reinforcement Learning Fall Symposium 2004.
    PDF

  • Proper, S., Tadepalli, P., Scaling Model-Based Average-reward Reinforcement Learning for Product Delivery,
    in ECML 2006: Proceedings of the 17th European Conference on Machine Learning, p 735-742.
    PDF

  • Proper, S., Tadepalli, P., Solving Multiagent Assignment Markov Decision Processes,
    in AAMAS 2009: Proceedings of the 8th International Joint Conference on Autonomous Agents and Multiagent Systems., p 681-688
    PDF

  • Proper, S., Tadepalli, P., Transfer Learning via Relational Templates,
    in ILP 2009: Proceedings of the 19th International Joint Conference on Inductive Logic Programming.
    PDF

    Scott Proper, proper@eecs.oregonstate.edu