Linghui Meng(孟令辉)

About me

I'm a Fourth-year PhD Student in CASIA working in multi-agent reinforcement learning. I graduated from Beijing Jiaotong University in July 2019.

I am interested in probabilistic graphical model, generative model, contrastive learning and multi-agent reinforcement learning. Recently I worked on MARL applied on video game and route packeging. I also serve as a reviewer on International Conference on Machine Learning (ICML) and Neural Information Processing Systems (NeurIPS).

News!

1. March. 17. 2022: Invited talk on How to pre-train a really large model with many GPUs? at the experimental class of direct doctoral students in CASIA.
2. June. 2021: I have been chosen as a member of the first experimental class of direct doctoral students in CASIA

Publications

1. One paper about offline multi-agent reinforcement learning accepted (To appear at AAMAS 2023) Linghui Meng, Jingqing Ruan, Xuantang Xiong, Dengpeng Xing, Bo Xu
2. Promoting Coordination Through Electing First-move Agent in Multi-Agent Reinforcement Learning (To appear at ICAPS 2022) Jingqing Ruan*, Linghui Meng*, Xuantang Xiong, Dengpeng Xing, Bo Xu
3. GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning (To appear at AAMAS 2022) Jingqing Ruan, Yali Du, Xuantang Xiong, Dengpeng Xing, Xiyun Li, Linghui Meng, Haifeng Zhang, Jun Wang, Bo Xu
4. Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Conquers All StarCraftII Tasks (Submitted) Linghui Meng, Muning Wen, Yaodong Yang, Chenyang Le, Xiyun Li, Weinan Zhang, Ying Wen, Haifeng Zhang, Jun Wang, Bo Xu
5. Settling the Variance of Multi-Agent Policy Gradients (To appear at NeurIPS 2021) Jakub Grudzien Kuba, Muning Wen, Linghui Meng, Shangding Gu, Haifeng Zhang, David Henry Mguni, Jun Wang, Yaodong Yang
6. MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition (To appear at ICASSP 2021) Linghui Meng, Jin Xu, Xu Tan, Jindong Wang, Tao Qin, Bo Xu

Other writings

1. Slides to clarify the development of MARL.
2. Overview of Google Football Environment.
3. Slides of GMM-HMM in ASR.
4. 多智能体强化学习环境-星际争霸2介绍

Useful links