MYMeiyi Yang
Meiyi Yang
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Meiyi Yang has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Huimin Gao
School of Information Engineering, Henan University of Science and Technology, Luoyang, China
2 shared publications Qingtao Wu
School of Information Engineering, Henan University of Science and Technology, Luoyang, China
2 shared publicationsDeng-Shan Shiau
Optima Neuroscience, Inc
1 shared publicationGaofeng Chen
1 shared publicationJ. Ch. Sackellares
Optima Neuroscience, Inc
1 shared publicationJiamei Feng
1 shared publication
Latest Publications
- Open Access
- 28 October 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (9) , 966
Provable mean-field Langevin neural actor-critic algorithms for multi-objective reinforcement learning
Actor-critic methods with theoretical convergence guarantees constitute an important class of algorithms for multi-objective reinforcement learning. To date, existing provable multi-objective actor-critic algorithms are limited to linear critic approximation and conventional stochastic actor updates. Consequently, a gap remains between the theoretical understanding of multi-objective actor-critic methods and the empirical success of deep neural actor-critic algorithms. To fill this gap, we propose a provable M ean- F ield L angevin M ulti- O bjective N eural A ctor- C ritic algorithm, referred to as MFL-MONAC, where mean-field Langevin dynamics is incorporated into both objective-wise critic evaluation and Pareto-guided actor improvement. Concretely, the critic performs regularized mean-field Langevin policy evaluation for each objective, while the actor uses MGDA-based gradient aggregation with momentum to construct a Pareto-guided update direction and applies mean-field Langevin dynamics to induce controlled particle-level exploration. We further establish a finite-time analysis for the MFL-MONAC algorithm, i.e., we show that the MFL-MONAC algorithm achieves ε -Pareto stationarity at a rate of $${{\mathcal{O}}}(1/\sqrt{T})$$ , where T is the number of iterations. Moreover, MFL-MONAC achieves a sufficient sample complexity of $${{\mathcal{O}}}({\varepsilon }^{-6})$$ . Finally, we conduct experiments on representative MORL benchmarks to demonstrate the effectiveness of MFL-MONAC.- 28 October 2026
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 38 (9) , 966
Open AccessProvable mean-field Langevin neural actor-critic algorithms for multi-objective reinforcement learning
Actor-critic methods with theoretical convergence guarantees constitute an important class of algorithms for multi-objective reinforcement learning. To date, existing provable multi-objective actor-critic algorithms are limited to linear critic approximation and conventional stochastic actor updates. Consequently, a gap remains between the theoretical understanding of multi-objective actor-critic methods and the empirical success of deep neural actor-critic algorithms. To fill this gap, we propose a provable M ean- F ield L angevin M ulti- O bjective N eural A ctor- C ritic algorithm, referred to as MFL-MONAC, where mean-field Langevin dynamics is incorporated into both objective-wise critic evaluation and Pareto-guided actor improvement. Concretely, the critic performs regularized mean-field Langevin policy evaluation for each objective, while the actor uses MGDA-based gradient aggregation with momentum to construct a Pareto-guided update direction and applies mean-field Langevin dynamics to induce controlled particle-level exploration. We further establish a finite-time analysis for the MFL-MONAC algorithm, i.e., we show that the MFL-MONAC algorithm achieves ε -Pareto stationarity at a rate of $${{\mathcal{O}}}(1/\sqrt{T})$$ , where T is the number of iterations. Moreover, MFL-MONAC achieves a sufficient sample complexity of $${{\mathcal{O}}}({\varepsilon }^{-6})$$ . Finally, we conduct experiments on representative MORL benchmarks to demonstrate the effectiveness of MFL-MONAC. - Open Access
- 1 July 2011
- Published by Springer Nature in Cybernetics and Systems Analysis
- Vol. 47 (4) , 586-597
A signal regularity-based automated seizure prediction algorithm using long-term scalp EEG recordings
- 1 July 2011
- Published by Springer Nature in Cybernetics and Systems Analysis
- Vol. 47 (4) , 586-597
Open AccessA signal regularity-based automated seizure prediction algorithm using long-term scalp EEG recordings