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 | 46 | 2021 |
A reinforcement learning approach to parameter selection for distributed optimal power flow S Zeng, A Kody, Y Kim, K Kim, DK Molzahn Electric Power Systems Research 212, 108546, 2022 | 26* | 2022 |
Finite-time complexity of online primal-dual natural actor-critic algorithm for constrained Markov decision processes S Zeng, TT Doan, J Romberg 2022 IEEE 61st Conference on Decision and Control (CDC), 4028-4033, 2022 | 22 | 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 | 21 | 2024 |
Fast compressive sensing recovery using generative models with structured latent variables S Xu, S Zeng, J Romberg ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019 | 21 | 2019 |
Regularized gradient descent ascent for two-player zero-sum Markov games S Zeng, T Doan, J Romberg Advances in Neural Information Processing Systems 35, 34546-34558, 2022 | 20 | 2022 |
Finite-time analysis of decentralized stochastic approximation with applications in multi-agent and multi-task learning S Zeng, TT Doan, J Romberg 2021 60th IEEE Conference on Decision and Control (CDC), 2641-2646, 2021 | 18 | 2021 |
Finite-time convergence rates of decentralized stochastic approximation with applications in multi-agent and multi-task learning S Zeng, TT Doan, J Romberg IEEE Transactions on Automatic Control 68 (5), 2758-2773, 2022 | 11 | 2022 |
Fast two-time-scale stochastic gradient method with applications in reinforcement learning S Zeng, T Doan The Thirty Seventh Annual Conference on Learning Theory, 5166-5212, 2024 | 4 | 2024 |
Connected superlevel set in (deep) reinforcement learning and its application to minimax theorems S Zeng, T Doan, J Romberg Advances in Neural Information Processing Systems 36, 20146-20163, 2023 | 4 | 2023 |
Sequential fair resource allocation under a markov decision process framework P Hassanzadeh, E Kreacic, S Zeng, Y Xiao, S Ganesh Proceedings of the Fourth ACM International Conference on AI in Finance, 673-680, 2023 | 2 | 2023 |
A Single-Loop Finite-Time Convergent Policy Optimization Algorithm for Mean Field Games (and Average-Reward Markov Decision Processes) S Zeng, S Bhatt, A Koppel, S Ganesh arXiv preprint arXiv:2408.04780, 2024 | 1 | 2024 |
A Policy Optimization Approach to the Solution of Unregularized Mean Field Games S Zeng, S Bhatt, A Koppel, S Ganesh ICML 2024 Workshop: Foundations of Reinforcement Learning and Control …, 2024 | 1 | 2024 |
Near-Optimal Fair Resource Allocation for Strategic Agents without Money: A Data-Driven Approach S Zeng, S Bhatt, E Kreacic, P Hassanzadeh, A Koppel, S Ganesh arXiv preprint arXiv:2311.10927, 2023 | 1 | 2023 |
Approximate Equivariance in Reinforcement Learning JY Park, S Bhatt, S Zeng, LLS Wong, A Koppel, S Ganesh, R Walters arXiv e-prints, arXiv: 2411.04225, 2024 | | 2024 |
ADAGE-Diff: Two-level adaptive agent based modelling for differentiable policy design BP Evans, S Zeng, S Ganesh, L Ardon NeurIPS 2024 Workshop on Data-driven and Differentiable Simulations …, 2024 | | 2024 |
Partially Observable Contextual Bandits with Linear Payoffs S Zeng, S Bhatt, A Koppel, S Ganesh arXiv preprint arXiv:2409.11521, 2024 | | 2024 |
Accelerated Multi-Time-Scale Stochastic Approximation: Optimal Complexity and Applications in Reinforcement Learning and Multi-Agent Games S Zeng, TT Doan arXiv preprint arXiv:2409.07767, 2024 | | 2024 |
QCQP-Net: Reliably Learning Feasible Alternating Current Optimal Power Flow Solutions Under Constraints S Zeng, Y Kim, Y Ren, K Kim 6th Annual Learning for Dynamics & Control Conference 242, 1539-1551, 2024 | | 2024 |
Method and system for sequential resource allocation Z Sihan, P Hassanzadeh, E Kreacic, S Ganesh US Patent App. 18/232,053, 2024 | | 2024 |