I am a PhD student in the College of Information and Computer Sciences at UMass Amherst. I work with Prof. Philip Thomas in the Autonmous Learning Labratory. I am interested in reinforcement learning and representation learning, with an emphasis on developing and evaluting practical algorithms for real world use.
Publications and Papers
- Learning a Better Negative Sampling Policy with Deep Neural Networks for Search
Daniel Cohen, Scott M. Jordan, W. Bruce Croft, Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval
- Evaluating Reinforcement learning Algorithms Using Cumulative Distributions of Performance
Scott M. Jordan, Yash Chandak, Mengxue Zhang, Daniel Cohen, Philip S. Thomas, Fourth Multidisciplinary Conference on Reinforcement learning and Decision Making (RLDM) 2019.
- Learning Action Representations for Reinforcement Learning
Yash Chandak, Georgios Theocharous, James Kostas, Scott M. Jordan, Philip S. Thomas, In Proceedings of the 36th International Conference on Machine Learning (ICML) 2019.
- Using Cumulative Distribution Based Performance Analysis to Benchmark Models
Scott M. Jordan, Daniel Cohen, Philip S. Thomas, In Critiquing and Correcting Trends in ML Workshop, NeurIPS 2018.
- Distributed Evaluations: Ending Neural Point Metrics
Daniel Cohen, Scott M. Jordan, W. Bruce Croft, SIGIR 2018 Workshop on Learning from Limited or Noisy Data
- Learning to Use a Ratchet by Modeling Spatial Relations in Demonstrations
Li Yang Ku, Scott M. Jordan, Julia Badger, Erik Learned-Miller, and Rod A. Grupen, Workshop on Learning from Demonstrations for High Level Robotics Tasks, at Robotics: Science and Systems 2018
- Summary of Experiments in Belief-Space Planning at the laboratory for Perceptual Robotics
Scott M. Jordan, Dirk Ruiken, Tiffany Q. Liu, Takeshi Takahashi, Michael W. Lanighan, Roderic A. Grupen, AAAI Spring Symposium 2017.