Research Interests

Education

2019 - 2024 | University of Alberta

Ph.D. Computing Science
2016 - 2018 | University of Alberta

M.Sc. Computing Science
2009 - 2014 | University of British Columbia

B.A.Sc. Mechanical Engineering (Mechatronics)

Openmind Research Institute \| Research Fellow	Aug 2024 - Present
Algorithms for learning in real-time from sensorimotor experience.
UAlberta RLAI Laboratory \| Research Assistant	Sep 2016 - Jun 2024
Online, incremental algorithms for value-based prediction and control in reinforcement learning.
Google Deepmind \| Research Scientist Intern	Mar 2021 - Jul 2021
Long-term temporal credit assignment in reinforcement learning.
Huawei Technologies Canada \| Research Associate	Apr 2019 - Aug 2019
Reinforcement learning applied to self-driving cars.
UAlberta Vision & Robotics Laboratory \| Research Assistant	Jun 2016 - Aug 2016
Reinforcement learning for human-robot interaction and robot learning-from-demonstration.
UBC Brain Behaviour Laboratory \| Laboratory Engineer	Jan 2013 - Jun 2016
Soft-, firm-, and hardware development supporting stroke rehabilitation research

Wadden, K., Hodges, N., De Asis, K., Neva, J., Boyd, L. (2018). Individualized challenge point practice as a method to aid motor sequence learning. Journal of Motor Behavior.
Wadden, K., De Asis, K., Mang, C., Neva, J., Peters, S., Lakhani, B., Boyd, L. (2016). Predicting motor sequence learning in individuals with chronic stroke. Neurorehabilitation & Neural Repair.

De Asis, K., Sutton, R. S. (2024). An idiosyncrasy of time-discretization in reinforcement learning. RLC 2024.
De Asis, K., Graves, E., Sutton, R. S. (2023). Value-aware importance weighting for off-policy reinforcement learning. CoLLAs 2023.
De Asis, K., Chan, A., Pitis, S., Sutton, R. S., Graves, D. (2020). Fixed-horizon temporal difference methods for stable reinforcement learning. AAAI 2020.
De Asis, K., Sutton, R. S. (2018). Per-decision multi-step temporal difference learning with control variates. UAI 2018.
De Asis, K.*, Hernandez-Garcia, J. F.*, Holland G. Z.*, Sutton, R. S. (2018). Multi-step reinforcement learning: a unifying algorithm. AAAI 2018.

Chan, A.*, De Asis, K.*, Sutton, R. S. (2022). Inverse policy evaluation for value-based decision making. RLDM 2022.
De Asis, K., Bennett, B., Sutton, R. S. (2019). Predicting periodicity with temporal difference learning. RLDM 2019.

De Asis, K., Elsayed, M. (2025). Extending differential temporal difference methods to episodic problems. Under review.
De Asis, K. (2024). Explorations in the foundations of value-based reinforcement learning. Ph.D. thesis, University of Alberta.
De Asis, K. (2018). A unified view of multi-step temporal difference learning. Master's thesis, University of Alberta.