I am a PhD student in Mathematics at the University of Ottawa. Formely a MSc student in the Modelling and Computational Science program at the University of Ontario Institute of Technology.
I am directly involved in the continuing development of the ChemGymRL environment for use in the reinforcement learning field.
I was heavily involved in the development of the Heat Engine environments and the application of both evolutionary and gradient-based reinforcement learning algoritms to these environments.
My PhD research consists of studying how the access to information revealing actions affects the behavior of reinforcement learning agents and determining how the levels of available information changes the difficulty of a given reinforcement learning problem.
My MSc research consisted of using reinforcement learning methods based on genetic algorithms to reproduce thermodynamic cycles without prior knowledge of physics and studying optimal solutions to various common reinforcement learning environments.
Publications / Posters / Presentations
- C. Beeler, U. Yahorau, R. Coles, K. Mills, S. Whitelam, and I. Tamblyn, "Optimizing thermodynamic trajectories using evolutionary and gradient-based reinforcement learning", arXiv preprint, arXiv:1903.08543 (2021)
- C. Beeler, "Neural Networks", Lecture, A3MD ML Bootcamp, A3MD (August 2020 & September 2020)
- K. Mills, K. Ryczko, I. Luchak, A. Domurad, C. Beeler, and I. Tamblyn, "Extensive deep neural networks for transferring small scale learning to large scale systems", Chemical Science, 10, 4129-4140 (2019)
- C. Beeler, Xinkai Li, Zihan Yang, Mark Crowley, and Isaac Tamblyn, "Navigating Chemistry", Invited Oral Presentation, Ottawa-AI Workshop 2019, Ottawa-AI Alliance (November 2019)
- C. Beeler, U. Yahorau, R. Coles, K. Mills, S. Whitelam, and I. Tamblyn, "Learning to work efficiently: Using neuroevolutionary strategies for reinforcement learning on classical thermodynamic systems", Oral Presentation, Physics & AI Workshop, McGill University (May 2019)
- C.Beeler and I. Tamblyn, "Perpetually Playing Physics", Modelling and Computational Science Seminar, University of Ontario Institute of Technology (April 2019)
- C. Beeler, U. Yahorau, R. Coles, K. Mills, S. Whitelam, and I. Tamblyn, "Maximizing thermal efficiency of heat engines using neuroevolutionary strategies for reinforcement learning", Oral Presentation, March Meeting 2019, American Physical Society (March 2019)
- K. Ryczko, C. Beeler, R. Coles, A. Domurad, C. Homenick, I. Luchak, K. Mills, D. Strubbe, U. Yahorau, and I. Tamblyn, "Machine learning for molecules", Poster Presentation, 32nd Conference on Neural Information Processing Systems, NeurIPS (December 2018)
- University of Ottawa Admission Scholarship (2019-Present)