Melrose Roderick's Picture

Melrose Roderick

Postdoctoral Researcher
Mila - Quebec AI Institute


I am a postdoc researcher at Mila working with Marc G. Bellemare and Glen Berseth. My research focuses on improving safety and robustness of reinforcement learning algorithms, allowing such methods to be applied to real-world problems, with a particular interest in environmental sustainability. I am currently applying these approaches to improve the energy efficiency and stability of fusion reactors.

Previously, I completed my Ph.D. at Carnegie Mellon University advised by Zico Kolter's. My thesis committee included Ruslan Salakhutdinov, Jeff Schneider, and Felix Berkenkamp. My work was supported by an NSF Graduate Research Fellowship. I received my B.Sc. at Brown University in Applied Math and Computer Science.

If you would like to schedule a meeting, please use my Calendly.

Publications

Deep Abstract Q-Networks

Deep Abstract Q-Networks

Melrose Roderick, Christopher Grimm, and Stefanie Tellex
Proceedings of the 17th International Conference on Autonomous Agents and Multi Agent Systems (AAMAS), 2018, (Nominated for best student paper)
[poster]   [code]

Mean Actor Critic

Mean Actor Critic

Kavosh Asadi, Cameron Allen, Melrose Roderick, Abdel-rahman Mohamed, George Konidaris, Michael Littman
arXiv preprint arXiv:1709.00503, 2017