Urmăriți
Alec Koppel
Alec Koppel
Research Lead, JP Morgan AI Research
Adresă de e-mail confirmată pe jpmchase.com - Pagina de pornire
Titlu
Citat de
Citat de
Anul
Global convergence of policy gradient methods to (almost) locally optimal policies
K Zhang, A Koppel, H Zhu, T Basar
SIAM Journal on Control and Optimization 58 (6), 3586-3612, 2020
2412020
A saddle point algorithm for networked online convex optimization
A Koppel, FY Jakubiec, A Ribeiro
IEEE Transactions on Signal Processing 63 (19), 5149-5164, 2015
2012015
A Class of Prediction-Correction Methods for Time-Varying Convex Optimization
A Simonetto, A Mokhtari, A Koppel, G Leus, A Ribeiro
IEEE Transactions on Signal Processing (submitted), 0
170*
Variational policy gradient method for reinforcement learning with general utilities
J Zhang, A Koppel, AS Bedi, C Szepesvari, M Wang
Advances in Neural Information Processing Systems 33, 4572-4583, 2020
1692020
On the sample complexity of actor-critic method for reinforcement learning with function approximation
H Kumar, A Koppel, A Ribeiro
Machine Learning 112 (7), 2433-2467, 2023
1242023
Proximity without consensus in online multi-agent optimization
A Koppel, BM Sadler, A Ribeiro
Proc. Int. Conf. Accoustics Speech Signal Proces (submitted),, 2016
952016
A Decentralized Prediction-Correction Method for Networked Time-Varying Convex Optimization
A Simonetto, A Mokhtari, A Koppel, G Leus, A Ribeiro
Computational Advances in Multi-Sensor Adaptive Processing, IEEE …, 2015
912015
MaxMin-RLHF: Alignment with diverse human preferences
S Chakraborty, J Qiu, H Yuan, A Koppel, F Huang, D Manocha, AS Bedi, ...
arXiv preprint arXiv:2402.08925, 2024
792024
Achieving zero constraint violation for constrained reinforcement learning via primal-dual approach
Q Bai, AS Bedi, M Agarwal, A Koppel, V Aggarwal
Proceedings of the AAAI Conference on Artificial Intelligence 36 (4), 3682-3689, 2022
782022
Decentralized online learning with kernels
A Koppel, S Paternain, C Richard, A Ribeiro
IEEE Transactions on Signal Processing 66 (12), 3240-3255, 2018
642018
Parsimonious online learning with kernels via sparse projections in function space
A Koppel, G Warnell, E Stump, A Ribeiro
The Journal of Machine Learning Research 20 (1), 83-126, 2019
582019
Parsimonious online learning with kernels via sparse projections in function space
A Koppel, G Warnell, E Stump, A Ribeiro
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
472017
Asynchronous and parallel distributed pose graph optimization
Y Tian, A Koppel, AS Bedi, JP How
IEEE Robotics and Automation Letters 5 (4), 5819-5826, 2020
442020
Consistent online gaussian process regression without the sample complexity bottleneck
A Koppel, H Pradhan, K Rajawat
Statistics and Computing 31, 1-18, 2021
402021
D4L: Decentralized Dynamic Discrminative Dictionary Learning
A Koppel, G Warnell, E Stump, A Ribeiro
IEEE Transactions on Signal and Info. Processing over Networks, 2015
402015
Cautious reinforcement learning via distributional risk in the dual domain
J Zhang, AS Bedi, M Wang, A Koppel
IEEE Journal on Selected Areas in Information Theory 2 (2), 611-626, 2021
382021
Policy Evaluation in Continuous MDPs with Efficient Kernelized Gradient Temporal Difference
A Koppel, G Warnell, E Stump, P Stone, A Ribeiro.
IEEE Transactions on Automatic Control 66 (4), 2020
33*2020
Asynchronous online learning in multi-agent systems with proximity constraints
AS Bedi, A Koppel, K Rajawat
IEEE Transactions on Signal and Information Processing over Networks 5 (3 …, 2019
312019
Asynchronous Decentralized Stochastic Optimization in Heterogeneous Networks
AS Bedi, A Koppel, K Rajawat
IEEE Trans. Signal Process (submitted)., 2017
31*2017
A variational approach to dual methods for constrained convex optimization
M Fazlyab, A Koppel, VM Preciado, A Ribeiro
2017 American Control Conference (ACC), 5269-5275, 2017
302017
Sistemul nu poate realiza operația în acest moment. Încercați din nou mai târziu.
Articole 1–20