Παρακολούθηση
Taylor W. Killian
Taylor W. Killian
Graduate Researcher, University of Toronto
Η διεύθυνση ηλεκτρονικού ταχυδρομείου έχει επαληθευτεί στον τομέα cs.toronto.edu - Αρχική σελίδα
Τίτλος
Παρατίθεται από
Παρατίθεται από
Έτος
Optimization methods for interpretable differentiable decision trees applied to reinforcement learning
A Silva, M Gombolay, T Killian, I Jimenez, SH Son
International conference on artificial intelligence and statistics, 1855-1865, 2020
180*2020
Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes
TW Killian, S Daulton, F Doshi-Velez, G Konidaris
Advances in Neural Information Processing Systems, 6251-6262, 2017
1322017
Medical dead-ends and learning to identify high-risk states and treatments
M Fatemi, TW Killian, J Subramanian, M Ghassemi
Advances in Neural Information Processing Systems 34, 4856-4870, 2021
522021
An empirical study of representation learning for reinforcement learning in healthcare
TW Killian, H Zhang, J Subramanian, M Fatemi, M Ghassemi
Proceedings of the Machine Learning for Health NeurIPS Workshop 136, 139-160, 2020
482020
Direct Policy Transfer with Hidden Parameter Markov Decision Processes
J Yao, TW Killian, G Konidaris, F Doshi-Velez
Lifelong Learning: A Reinforcement Learning Approach Workshop at FAIM 2018, 2018
32*2018
Rebound and jet formation of a fluid-filled sphere
TW Killian, RA Klaus, TT Truscott
Physics of Fluids 24 (12), 2012
132012
Counterfactually guided policy transfer in clinical settings
TW Killian, M Ghassemi, S Joshi
Conference on Health, Inference, and Learning, 5-31, 2022
122022
Multiple sclerosis severity classification from clinical text
AD Costa, S Denkovski, M Malyska, SY Moon, B Rufino, Z Yang, T Killian, ...
arXiv preprint arXiv:2010.15316, 2020
122020
Transfer Learning Across Patient Variations with Hidden Parameter Markov Decision Processes
T Killian, G Konidaris, F Doshi-Velez
arXiv preprint arXiv:1612.00475, 2016
122016
Risk Sensitive Dead-end Identification in Safety-Critical Offline Reinforcement Learning
TW Killian, S Parbhoo, M Ghassemi
Transactions on Machine Learning Research, 2023
102023
Kernelized capsule networks
T Killian, J Goodwin, O Brown, SH Son
arXiv preprint arXiv:1906.03164, 2019
62019
White-box adversarial policies in deep reinforcement learning
S Casper, T Killian, G Kreiman, D Hadfield-Menell
arXiv preprint arXiv:2209.02167, 2022
52022
Machine learning for health (ml4h) 2022
A Parziale, M Agrawal, S Tang, K Severson, L Oala, A Subbaswamy, ...
Machine Learning for Health, 1-11, 2022
32022
Systems and methods for detection of concealed threats
MA Deangelus, J Goodwin, N Kaushik, A Opipari, T Killian
US Patent App. 17/219,837, 2022
12022
Red teaming with mind reading: White-box adversarial policies against rl agents
S Casper, T Killian, G Kreiman, D Hadfield-Menell
arXiv preprint arXiv:2209.02167, 2022
12022
Self healing: solid spheres impacting soap bubbles
T Killian, J Bryson, J Huey, JC Bird, JC Nave, T Truscott
APS Division of Fluid Dynamics Meeting Abstracts, R4. 005, 2012
1*2012
Robust Autonomy Emerges from Self-Play
M Cusumano-Towner, D Hafner, A Hertzberg, B Huval, A Petrenko, ...
arXiv preprint arXiv:2502.03349, 2025
2025
Identifying Differential Patient Care Through Inverse Intent Inference
H Jeong, S Nayak, T Killian, S Kanjilal, M Ghassemi
arXiv preprint arXiv:2411.07372, 2024
2024
Offline Reinforcement Learning With Combinatorial Action Spaces
M Landers, TW Killian, H Barnes, T Hartvigsen, A Doryab
arXiv preprint arXiv:2410.21151, 2024
2024
Clinically Motivated Sequential Decision Making Under Uncertainty in Offline Settings
TW Killian
University of Toronto (Canada), 2024
2024
Δεν είναι δυνατή η εκτέλεση της ενέργειας από το σύστημα αυτή τη στιγμή. Προσπαθήστε ξανά αργότερα.
Άρθρα 1–20