A. Rupam Mahmood
A. Rupam Mahmood
University of Alberta, Amii
Patvirtintas el. paštas - Pagrindinis puslapis
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
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
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
True online temporal-difference learning
H van Seijen, AR Mahmood, PM Pilarski, MC Machado, RS Sutton
(JMLR) Journal of Machine Learning Research 17, 2016
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
Tuning-free step-size adaptation
AR Mahmood, RS Sutton, T Degris, PM Pilarski
(ICASSP) Acoustics, Speech and Signal Processing, 2012 IEEE International …, 2012
Maintaining plasticity in deep continual learning
S Dohare, JF Hernandez-Garcia, P Rahman, AR Mahmood, RS Sutton
arXiv preprint arXiv:2306.13812, 2024
Multi-step off-policy learning without importance sampling ratios
AR Mahmood, H Yu, RS Sutton
arXiv preprint arXiv:1702.03006, 2017
Representation Search through Generate and Test
AR Mahmood, RS Sutton
Workshops at the Twenty-Seventh AAAI Conference on Artificial Intelligence, 2013
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
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
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
Emphatic temporal-difference learning
AR Mahmood, H Yu, M White, RS Sutton
In European Workshops on Reinforcement Learning, 2015
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
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
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
Incremental Off-policy Reinforcement Learning Algorithms
A Mahmood
University of Alberta, 2017
Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
H Ishfaq*, Q Lan*, P Xu, AR Mahmood, D Precup, A Anandkumar, ...
(ICLR) International Conference on Learning Representations, 2024
Asynchronous reinforcement learning for real-time control of physical robots
Y Yuan, AR Mahmood
(ICRA) In Proceedings of the 2022 International Conference on Robotics and …, 2022
Structure Learning of Causal Bayesian Networks: A Survey
A Mahmood
Department of Computing Science, University of Alberta, Edmonton, Canada …, 2011
Sistema negali atlikti operacijos. Bandykite vėliau dar kartą.
Straipsniai 1–20