Jun Wang Photo 

Jun Wang

Professor, Computer Science, University College London

Programme Director, MSc Web Science and Big Data Analytics

Email: jun.wang (at) cs.ucl.ac.uk

Office: 3.08 66-72 Gower Street, London

Co-founder, Chief Scientist, MediaGamma Ltd.

UCL Centre for Artificial Intelligence

I am looking for two summer interns on a topic related to AI and machine learning. If interested and have legal right to work in the UK over summer, contact me with your latest CV.

The latest talk on Multi-agent Learning at Peking University. The tutorial version will be given in Shanghai Jiao Tong University.

Research Interests

  • AI and Machine Learning, Multi-agent Reinforcement Learning, and Neural Generative Models;

  • Statistical Modeling of Information Retrieval, and Dynamic Information Retrieval;

  • Data Mining, Personalization, and Collaborative Filtering (Recommender Systems);

  • Computational Advertising and Real-time Bidding.

Selected Recent Papers

Multi-agent AI


Mean Field Multi-Agent Reinforcement Learning
Yaodong Yang, Rui Luo, Minne Li, Ming Zhou, Weinan Zhang, and Jun Wang
arXiv:1802.05438, 2018, draft


Learning to Design Games: Strategic Environments in Deep Reinforcement Learning
Haifeng Zhang, Jun Wang, Zhiming Zhou, Weinan Zhang, Ying Wen, Yong Yu, Wenxin Li
arXiv:1707.01310v3, 2018, draft


An Empirical Study of AI Population Dynamics with Million-agent Reinforcement Learning
Lianmin Zheng, Jiacheng Yang, Han Cai, Weinan Zhang, Jun Wang, and Yong Yu
arXiv:1709.04511v3, AAMAS 18

Text/Discrete GANs


Long Text Generation via Adversarial Training with Leaked Information
Jiaxian Guo, Sidi Lu, Han Cai, Weinan Zhang, Yong Yu, and Jun Wang
arXiv:1709.08624v1, AAAI-2018


IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models
Wang, Jun, Lantao Yu, Weinan Zhang, Yu Gong, Yinghui Xu, Benyou Wang, Peng Zhang, and Dell Zhang
SIGIR (Best Paper Award Honorable Mention), 2017


SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
Lantao Yu, Weinan Zhang, Jun Wang, Yong Yu
arXiv:1609.05473v6, AAAI, 2017

Neural Generative Models


Activation Maximization Generative Adversarial Nets
Zhiming Zhou, Han Cai, Shu Rong, Yuxuan Song, Kan Ren, Weinan Zhang, Yong Yu, and Jun Wang
arXiv:1703.02000v7, ICLR-2018


A Neural Stochastic Volatility Model
Rui Luo, Jun Wang, Weinan Zhang and Xiaojun Xu
arXiv:1712.00504, AAAI-2018


Adversarial Variational Inference for Tweedie Compound Poisson Models
Yaodong Yang, Sergey Demyanov, Yunayuan Liu, Jun Wang
arXiv:1706.05446v3, ICML Workshop on Implicit Models, 2017



Reinforcement Learning for Architecture Search by Network Transformation
Han Cai, Tianyao Chen, Weinan Zhang, Yong Yu, and Jun Wang
arXiv:1707.04873v1, AAAI-2018

For a full list, see my Google Scholar page.

Demos on Multi-agent AI

MAgent: A Many-Agent Reinforcement Learning Research Platform for Artificial Collective Intelligence
Lianmin Zheng, Jiacheng Yang, Han Cai, Weinan Zhang, Jun Wang, and Yong Yu
NIPS17 demo
arXiv:1712.00600, 2017
Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games
Peng Peng, Ying Wen, Yaodong Yang, Quan Yuan, Zhenkun Tang, Haitao Long, Jun Wang
arXiv:1703.10069v4, 2017
City Traffic Simulator/Optimizer
Each moving dot is driven by a neural network-based reinforcement learning agent
Collaborative Bots Sorting Parcels

Social Media