张恒溪|ZHANG Hengxi

张恒溪|ZHANG Hengxi

Tsinghua University

Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Pages

Posts

Future Blog Post

less than 1 minute read

Published:

This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.

Blog Post number 4

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 3

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 2

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

Blog Post number 1

less than 1 minute read

Published:

This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.

portfolio

publications

Published in , 1900

Heterogeneous Mean-Field Multi-Agent Reinforcement Learning for Communication Routing Selection in SAGI-Net

Published in 2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall), 2022

In this work, we represent a novel communication routing selection model for the SAGI-Net system and established a heterogeneous multi-agent reinforcement learning (HMF-MARL) framework to optimize the communication energy efficiency of this system, where the mean-field theory was introduced to enhance the ability of classic MARL method while still maintaining a relatively low computational complexity.

Recommended citation: Hengxi Zhang, Huaze Tang, Yuanquan Hu, Xiaoli Wei, Chenye Wu, Wenbo Ding, and Xiao-Ping Zhang. "Heterogeneous Mean-Field Multi-Agent Reinforcement Learning for Communication Routing Selection in SAGI-Net." In 2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall), pp. 1-5. IEEE, 2022. https://ieeexplore.ieee.org/abstract/document/10012942

Published in , 1900

Mean-Field-Aided Multiagent Reinforcement Learning for Resource Allocation in Vehicular Networks

Published in IEEE Internet of Things Journal, 2023

In this article, we propose a novel method MF-MARL that combines mean-field game with MARL to decrease the computational complexity in a decentralized multi-agent system while maintaining a near-optimal performance.

Recommended citation: Hengxi Zhang, Chengyue Lu, Huaze Tang, Xiaoli Wei, Le Liang, Ling Cheng, Wenbo Ding, and Zhu Han. " Mean-Field-Aided Multiagent Reinforcement Learning for Resource Allocation in Vehicular Networks." IEEE Internet of Things Journal 10, no. 3 (2022): 2667-2679. https://ieeexplore.ieee.org/abstract/document/9919273

Graphon Mean-Field Control for Cooperative Multi-Agent Reinforcement Learning

Published in Elsevier Journal of the Franklin Institute, 2023

In this paper, we introduce a graphon mean-field control framework that introduces graphon theory to the mean-field paradigm to approximate cooperative heterogeneous multi-agent reinforcement learning with nonuniform interactions and heterogeneous reward functions and state transition functions among agents.

Recommended citation: Yuanquan Hu, Xiaoli Wei, Junji Yan, Hengxi Zhang, Graphon Mean-Field Control for Cooperative Multi-Agent Reinforcement Learning, Journal of the Franklin Institute, Sept. 1, 2023 https://www.sciencedirect.com/science/article/pii/S0016003223005483

Published in , 1900

talks

teaching

From 0 to 1: Code the Classic Reinforcement Learning Algorithms

Programming Course, Bilibili, 2025

This coding series is designed to lead you from basic to advanced reinforcement learning by walking through hands-on Python implementations of the classic algorithms. Step by step, you’ll follow along as each method is explained and developed line by line, starting from the foundational Q-Learning and progressing through modern deep RL including DQN, DDPG, MADDPG, PPO, and SAC.

Mathematics in Reinforcement learning

Theoretical Course, Bilibili, 2025

This theoretical series is designed to walk you through the mathematical foundations that are central to modern RL algorithms. Throughout the course, we will cover key topics including unbiased versus biased estimations, the structure of Markov Decision Processes (MDPs), the mathematical definition and role of policies, value functions, and essential methods such as Monte Carlo sampling. Just come over and have fun