T. Doan

发表

Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance

Thinh T. Doan, T. Doan, 2020, IEEE Transactions on Automatic Control.

Linear Two-Time-Scale Stochastic Approximation A Finite-Time Analysis

Thinh T. Doan, Justin Romberg, Thinh T. Doan, 2019, 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

Performance of Q-learning with Linear Function Approximation: Stability and Finite-Time Analysis

Thinh T. Doan, Siva Theja Maguluri, J. Clarke, 2019 .

Finite-Time Analysis of Markov Gradient Descent

T. Doan, 2023, IEEE Transactions on Automatic Control.

Convergence Rates of Accelerated Markov Gradient Descent with Applications in Reinforcement Learning

Lam M. Nguyen, Thinh T. Doan, Nhan H. Pham, 2020, 2002.02873.

Finite-Time Analysis and Restarting Scheme for Linear Two-Time-Scale Stochastic Approximation pdf

Thinh T. Doan, Thinh T. Doan, T. Doan, 2019, SIAM J. Control. Optim..

Finite-Time Analysis of Stochastic Gradient Descent under Markov Randomness pdf

Lam M. Nguyen, Justin Romberg, Nhan H. Pham, 2020, ArXiv.

Finite-sample analysis of nonlinear stochastic approximation with applications in reinforcement learning

Thinh T. Doan, Sheng Zhang, Siva Theja Maguluri, 2019, Autom..

Byzantine Fault-Tolerance in Decentralized Optimization under 2f-Redundancy

Nitin H. Vaidya, Thinh T. Doan, Nirupam Gupta, 2021, 2021 American Control Conference (ACC).

Convergence Rates of Distributed Gradient Methods Under Random Quantization: A Stochastic Approximation Approach

Thinh T. Doan, Justin Romberg, Siva Theja Maguluri, 2021, IEEE Transactions on Automatic Control.

Convergence and Price of Anarchy Guarantees of the Softmax Policy Gradient in Markov Potential Games

Qi Zhang, T. Doan, Dingyang Chen, 2022, ArXiv.

Convergence Rates of Asynchronous Policy Iteration for Zero-Sum Markov Games under Stochastic and Optimistic Settings

Sarnaduti Brahma, T. Doan, Yitao Bai, 2022, 2022 IEEE 61st Conference on Decision and Control (CDC).

Federated Multi-Agent Deep Reinforcement Learning (Fed-MADRL) for Dynamic Spectrum Access

Lingjia Liu, Haowen Chang, Yifei Song, 2023, IEEE Transactions on Wireless Communications.

Local Stochastic Approximation: A Unified View of Federated Learning and Distributed Multi-Task Reinforcement Learning Algorithms pdf

Thinh T. Doan, T. Doan, 2020, ArXiv.

Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems

J. Romberg, Sihan Zeng, T. Doan, 2023, ArXiv.

Finite-Time Analysis of Q-Learning with Linear Function Approximation pdf

John-Paul Clarke, Thinh T. Doan, Sheng Zhang, 2019, ArXiv.

Finite-Time Analysis of Distributed TD(0) with Linear Function Approximation on Multi-Agent Reinforcement Learning

Thinh T. Doan, Justin Romberg, Siva Theja Maguluri, 2019, ICML.

Finite-Time Analysis of Decentralized Stochastic Approximation with Applications in Multi-Agent and Multi-Task Learning pdf

Thinh T. Doan, Sihan Zeng, Justin Romberg, 2020, 2021 60th IEEE Conference on Decision and Control (CDC).

Finite-Time Performance of Distributed Temporal Difference Learning with Linear Function Approximation pdf

Thinh T. Doan, Justin Romberg, Siva Theja Maguluri, 2019, SIAM J. Math. Data Sci..

Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes

Thinh T. Doan, J. Romberg, Sihan Zeng, 2021, IEEE Conference on Decision and Control.

Convergence Rates of Two-Time-Scale Gradient Descent-Ascent Dynamics for Solving Nonconvex Min-Max Problems pdf

Thinh T. Doan, T. Doan, 2021, L4DC.

A Two-Time-Scale Stochastic Optimization Framework with Applications in Control and Reinforcement Learning

Thinh T. Doan, J. Romberg, Sihan Zeng, 2021, ArXiv.

Finite-Time Convergence Rates of Nonlinear Two-Time-Scale Stochastic Approximation under Markovian Noise pdf

Thinh T. Doan, T. Doan, 2021, ArXiv.

Finite-Sample Analysis of Two-Time-Scale Natural Actor–Critic Algorithm

Thinh T. Doan, Siva Theja Maguluri, J. Romberg, 2021, IEEE Transactions on Automatic Control.

A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learning

Thinh T. Doan, J. Romberg, A. Raychowdhury, 2020, UAI.

Distributed Lagrangian methods for network resource allocation

Thinh T. Doan, Carolyn L. Beck, T. Doan, 2016, 2017 IEEE Conference on Control Technology and Applications (CCTA).

Distributed resource allocation on dynamic networks in quadratic time

Thinh T. Doan, Alex Olshevsky, Alexander Olshevsky, 2015, Syst. Control. Lett..

Distributed Dual Subgradient Methods with Averaging and Applications to Grid Optimization

Carolyn L. Beck, S. Bose, H. Nguyen, 2021, 2107.07061.

Fast Convergence Rates of Distributed Subgradient Methods With Adaptive Quantization

Thinh T. Doan, Justin Romberg, Siva Theja Maguluri, 2018, IEEE Transactions on Automatic Control.

Accelerating the Convergence Rates of Distributed Subgradient Methods with Adaptive Quantization

Thinh T. Doan, Siva Theja Maguluri, J. Romberg, 2018, 1810.13245.

Distributed Stochastic Approximation for Solving Network Optimization Problems Under Random Quantization

Thinh T. Doan, Justin Romberg, Siva Theja Maguluri, 2018, 1810.11568.

On the Convergence of Distributed Subgradient Methods under Quantization

Thinh T. Doan, Justin Romberg, Siva Theja Maguluri, 2018, 2018 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

Convergence Rate of Distributed Subgradient Methods under Communication Delays

R. Srikant, Thinh T. Doan, Carolyn L. Beck, 2018, 2018 Annual American Control Conference (ACC).

Aggregating Stochastic Gradients in Distributed Optimization

Thinh T. Doan, T. Doan, 2018, 2018 Annual American Control Conference (ACC).

On the Convergence Rate of Distributed Gradient Methods for Finite-Sum Optimization under Communication Delays

R. Srikant, Thinh T. Doan, Carolyn L. Beck, 2017, Abstracts of the 2018 ACM International Conference on Measurement and Modeling of Computer Systems.

On the Convergence Rate of Distributed Gradient Methods for Finite-Sum Optimization under Communication Delays

R. Srikant, Thinh T. Doan, Carolyn L. Beck, 2017, Proc. ACM Meas. Anal. Comput. Syst..

Impact of Communication Delays on the Convergence Rate of Distributed Optimization Algorithms

Thinh T. Doan, Rayadurgam Srikant, Carolyn L. Beck, 2017, 1708.03277.

Distributed Grid Optimization via Distributed Dual Subgradient Methods with Averaging

Carolyn L. Beck, Hoa Dinh Nguyen, S. Bose, 2021, ArXiv.

Convergence Rates of Distributed Two-Time-Scale Gradient Methods under Random Quantization

Thinh T. Doan, Justin Romberg, Siva Theja Maguluri, 2019, IFAC-PapersOnLine.

Sequencing of multi-robot behaviors using reinforcement learning

Thinh T. Doan, J. Romberg, M. Egerstedt, 2021, Control Theory and Technology.

Convergence of the Iterates in Mirror Descent Methods

Thinh T. Doan, Carolyn L. Beck, Subhonmesh Bose, 2018, IEEE Control Systems Letters.

Distributed Dual Subgradient Methods with Averaging and Applications to Grid Optimization

Carolyn L. Beck, S. Bose, H. Nguyen, 2021, 2107.07061.

Regularized Gradient Descent Ascent for Two-Player Zero-Sum Markov Games

Thinh T. Doan, J. Romberg, Sihan Zeng, 2022, NeurIPS.

A Reinforcement Learning Framework for Sequencing Multi-Robot Behaviors pdf

Thinh T. Doan, Magnus Egerstedt, Justin Romberg, 2019, ArXiv.

Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems

J. Romberg, Sihan Zeng, T. Doan, 2023, NeurIPS.