| Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation for Multi-Agent Reinforcement Learning TT Doan, ST Maguluri, J Romberg International Conference on Machine Learning, 2019 | 169 | 2019 |
| Performance of Q-learning with Linear Function Approximation: Stability and Finite-Time Analysis Z Chen, S Zhang, TT Doan, ST Maguluri, JP Clarke arXiv preprint arXiv:1905.11425, 2019 | 143* | 2019 |
| Fast Convergence Rates of Distributed Subgradient Methods with Adaptive Quantization TT Doan, ST Maguluri, J Romberg arXiv preprint arXiv:1810.13245, 2018 | 89 | 2018 |
| Convergence rates of distributed gradient methods under random quantization: A stochastic approximation approach TT Doan, ST Maguluri, J Romberg IEEE Transactions on Automatic Control 66 (10), 4469-4484, 2020 | 76* | 2020 |
| Distributed resource allocation on dynamic networks in quadratic time TT Doan, A Olshevsky https://arxiv.org/abs/1507.07850, 2015 | 59 | 2015 |
| Finite-time performance of distributed temporal-difference learning with linear function approximation TT Doan, ST Maguluri, J Romberg SIAM Journal on Mathematics of Data Science 3 (1), 298-320, 2021 | 55 | 2021 |
| Convergence of the iterates in mirror descent methods TT Doan, S Bose, DH Nguyen, CL Beck IEEE control systems letters 3 (1), 114-119, 2018 | 55 | 2018 |
| Finite-sample analysis of two-time-scale natural actor–critic algorithm S Khodadadian, TT Doan, J Romberg, ST Maguluri IEEE Transactions on Automatic Control 68 (6), 3273-3284, 2022 | 50 | 2022 |
| A decentralized policy gradient approach to multi-task reinforcement learning S Zeng, MA Anwar, TT Doan, A Raychowdhury, J Romberg Uncertainty in Artificial Intelligence, 1002-1012, 2021 | 49 | 2021 |
| On the convergence rate of distributed gradient methods for finite-sum optimization under communication delays TT Doan, CL Beck, R Srikant arXiv preprint arXiv:1708.03277, 2017 | 48* | 2017 |
| Distributed Lagrangian Methods for Network Resource Allocation TT Doan, CL Beck arXiv preprint arXiv:1609.06287, 2016 | 46* | 2016 |
| Nonlinear two-time-scale stochastic approximation: Convergence and finite-time performance TT Doan IEEE Transactions on Automatic Control 68 (8), 4695-4705, 2022 | 44 | 2022 |
| Distributed resource allocation over dynamic networks with uncertainty TT Doan, CL Beck IEEE Transactions on Automatic Control, 2020 | 38 | 2020 |
| On the Convergence Rate of Distributed Gradient Methods for Finite-Sum Optimization under Communication Delays TT Doan, CL Beck, R Srikant Proceedings of the ACM on Measurement and Analysis of Computing Systems 1 (2 …, 2017 | 38 | 2017 |
| Finite-time analysis and restarting scheme for linear two-time-scale stochastic approximation TT Doan SIAM Journal on Control and Optimization 59 (4), 2798-2819, 2021 | 34 | 2021 |
| On the geometric convergence rate of distributed economic dispatch/demand response in power networks TT Doan, A Olshevsky arXiv preprint arXiv:1609.06660, 2016 | 33 | 2016 |
| Byzantine fault-tolerance in decentralized optimization under 2f-redundancy N Gupta, TT Doan, NH Vaidya 2021 American Control Conference (ACC), 3632-3637, 2021 | 27 | 2021 |
| Convergence rates of accelerated markov gradient descent with applications in reinforcement learning TT Doan, LM Nguyen, NH Pham, J Romberg arXiv preprint arXiv:2002.02873, 2020 | 27 | 2020 |
| Finite-time analysis of markov gradient descent TT Doan IEEE Transactions on Automatic Control 68 (4), 2140-2153, 2022 | 26 | 2022 |
| A two-time-scale stochastic optimization framework with applications in control and reinforcement learning S Zeng, TT Doan, J Romberg SIAM Journal on Optimization 34 (1), 946-976, 2024 | 22 | 2024 |
Justin RombergProfessor of Electrical and Computer Engineering, Georgia Institute of TechnologyVerificeret mail på ece.gatech.edu