עקוב אחר
A. Rupam Mahmood
A. Rupam Mahmood
University of Alberta, Amii
כתובת אימייל מאומתת בדומיין ualberta.ca - דף הבית
כותרת
צוטט על ידי
צוטט על ידי
שנה
An emphatic approach to the problem of off-policy temporal-difference learning‏
RS Sutton, AR Mahmood, M White‏
(JMLR) Journal of Machine Learning Research 17, 2016‏
3282016
Benchmarking reinforcement learning algorithms on real-world robots‏
AR Mahmood, D Korenkevych, G Vasan, W Ma, J Bergstra‏
(CoRL) Proceedings of the 2nd Annual Conference on Robot Learning, 2018‏
2352018
Weighted importance sampling for off-policy learning with linear function approximation‏
AR Mahmood, H van Hasselt, RS Sutton‏
(NeurIPS) Advances in Neural Information Processing Systems 27, 2014‏
1912014
True online temporal-difference learning‏
H van Seijen, AR Mahmood, PM Pilarski, MC Machado, RS Sutton‏
(JMLR) Journal of Machine Learning Research 17, 2016‏
1252016
Setting up a reinforcement learning task with a real-world robot‏
AR Mahmood, D Korenkevych, BJ Komer, J Bergstra‏
(IROS) 2018 IEEE/RSJ International Conference on Intelligent Robots and …, 2018‏
1062018
Tuning-free step-size adaptation‏
AR Mahmood, RS Sutton, T Degris, PM Pilarski‏
(ICASSP) Acoustics, Speech and Signal Processing, 2012 IEEE International …, 2012‏
892012
Continual backprop: Stochastic gradient descent with persistent randomness‏
S Dohare, RS Sutton, AR Mahmood‏
arXiv preprint arXiv:2108.06325, 2021‏
792021
Loss of plasticity in deep continual learning‏
S Dohare, JF Hernandez-Garcia, Q Lan, P Rahman, AR Mahmood, ...‏
Nature 632 (8026), 768-774, 2024‏
592024
Multi-step off-policy learning without importance sampling ratios‏
AR Mahmood, H Yu, RS Sutton‏
arXiv preprint arXiv:1702.03006, 2017‏
552017
Representation Search through Generate and Test‏
AR Mahmood, RS Sutton‏
Workshops at the Twenty-Seventh AAAI Conference on Artificial Intelligence, 2013‏
502013
Off-policy TD (λ) with a true online equivalence‏
H van Hasselt, AR Mahmood, RS Sutton‏
(UAI) Proceedings of the 30th Conference on Uncertainty in Artificial …, 2014‏
482014
On generalized Bellman equations and temporal-difference learning‏
H Yu, AR Mahmood, RS Sutton‏
(JMLR) The Journal of Machine Learning Research 19 (1), 1864-1912, 2018‏
422018
A new Q (λ) with interim forward view and Monte Carlo equivalence‏
RS Sutton, AR Mahmood, D Precup, M CA, H van Hasselt, U CA‏
(ICML) In International Conference on Machine Learning, 2014‏
402014
Emphatic temporal-difference learning‏
AR Mahmood, H Yu, M White, RS Sutton‏
In European Workshops on Reinforcement Learning, 2015‏
392015
Greedification operators for policy optimization: investigating forward and reverse KL divergences‏
A Chan, H Silva, S Lim, T Kozuno, AR Mahmood, M White‏
(JMLR) Journal of Machine Learning Research, 2022‏
352022
Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning‏
M Elsayed, AR Mahmood‏
(ICLR) The Twelfth International Conference on Learning Representations, 2024‏
32*2024
Off-policy learning based on weighted importance sampling with linear computational complexity‏
AR Mahmood, RS Sutton‏
(UAI) Proceedings of the 31st Conference on Uncertainty in Artificial …, 2015‏
322015
Maintaining plasticity in deep continual learning‏
S Dohare, JF Hernandez-Garcia, P Rahman, AR Mahmood, RS Sutton‏
arXiv preprint arXiv:2306.13812, 2023‏
292023
Autoregressive policies for continuous control deep reinforcement learning‏
D Korenkevych, AR Mahmood, G Vasan, J Bergstra‏
(IJCAI) Proceedings of the 28th International Joint Conference on Artificial …, 2019‏
292019
Incremental Off-policy Reinforcement Learning Algorithms‏
A Mahmood‏
University of Alberta, 2017‏
222017
המערכת אינה יכולה לבצע את הפעולה כעת. נסה שוב מאוחר יותר.
מאמרים 1–20