Obserwuj
Navdeep Kumar
Navdeep Kumar
Technion
Zweryfikowany adres z campus.technion.ac.il
Tytuł
Cytowane przez
Cytowane przez
Rok
Policy gradient for rectangular robust markov decision processes
N Kumar, E Derman, M Geist, KY Levy, S Mannor
Advances in Neural Information Processing Systems 36, 59477-59501, 2023
352023
Efficient value iteration for s-rectangular robust Markov decision processes
N Kumar, K Wang, KY Levy, S Mannor
Forty-first International Conference on Machine Learning, 2024
29*2024
Towards faster global convergence of robust policy gradient methods
N Kumar, I Usmanova, KY Levy, S Mannor
Sixteenth European Workshop on Reinforcement Learning, 2023
92023
The effect of network delays on distributed ledgers based on Directed Acyclic Graphs: a mathematical model
N Kumar, A Reiffers-Masson, I Amigo, SR Rincon
Performance Evaluation 163, 102392, 2024
82024
The geometry of robust value functions
K Wang, N Kumar, K Zhou, B Hooi, J Feng, S Mannor
International Conference on Machine Learning, 22727-22751, 2022
72022
Global Convergence of Policy Gradient in Average Reward MDPs
N Kumar, Y Murthy, I Shufaro, KY Levy, R Srikant, S Mannor
The Thirteenth International Conference on Learning Representations, 0
7*
Bring your own (non-robust) algorithm to solve robust MDPs by estimating the worst kernel
U Gadot, K Wang, N Kumar, KY Levy, S Mannor
Forty-first International Conference on Machine Learning, 2024
5*2024
Policy gradient for reinforcement learning with general utilities
N Kumar, K Wang, K Levy, S Mannor
arXiv preprint arXiv:2210.00991, 2022
32022
Solving non-rectangular reward-robust MDPs via frequency regularization
U Gadot, E Derman, N Kumar, MM Elfatihi, K Levy, S Mannor
Proceedings of the AAAI Conference on Artificial Intelligence 38 (19), 21090 …, 2024
22024
Dual Formulation for Non-Rectangular Lp Robust Markov Decision Processes
N Kumar, A Gupta, MM Elfatihi, G Ramponi, KY Levy, S Mannor
arXiv preprint arXiv:2502.09432, 2025
2025
Improved Sample Complexity for Global Convergence of Actor-Critic Algorithms
N Kumar, P Agrawal, G Ramponi, KY Levy, S Mannor
arXiv preprint arXiv:2410.08868, 2024
2024
Learning the Uncertainty Set in Robust Markov Decision Process
N Kumar, K Wang, U Gadot, KY Levy, S Mannor
The Second Tiny Papers Track at ICLR 2024, 0
Policy Gradient with Tree Search (PGTS) in Reinforcement Learning Evades Local Maxima
N Kumar, P Agrawal, KY Levy, S Mannor
The Second Tiny Papers Track at ICLR 2024, 0
Targeted Uncertainty Reduction in Robust MDPs
U Gadot, K Wang, E Derman, N Kumar, K Levy, S Mannor
NeurIPS 2023 Workshop on Generalization in Planning, 0
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–14