梁洪

个人简介

博士毕业于西安交通大学数学专业，主要从事平均场博弈与强化学习相关研究，重点研究基于深度强化学习的平均场博弈求解方法，关注连续状态与动作空间下的算法设计、理论分析及其应用。相关研究涉及随机控制、多智能体系统与大规模群体决策等方向。

科研论著

[1] Liang H, Chen Z, Jing K. Actor-critic reinforcement learning algorithms for mean field games in continuous time, state and action spaces[J]. Applied Mathematics & Optimization, 2024, 89(3): 72.

[2] Liang H, Chen Z, Yang P, Wang L. Necessary and sufficient conditions for open-loop equilibrium portfolio for a DC pension plan with piecewise linear state-dependent risk tolerance[J]. Communications in Statistics-Theory and Methods, 2025, 54(13): 4001-4016.

[3] Liang H, Zhou J. Infinite horizon optimal control problems of backward stochastic delay differential equations in Hilbert spaces[J]. Bulletin of the Korean Mathematical Society, 2020, 57(2): 311-330.