 |
Jun WangProfessor, Computer Science, University College London UCL Centre for Artificial Intelligence Email: jun.wang (at) cs.ucl.ac.uk Office: 3.08 66-72 Gower Street, London Turing Fellow, the Alan Turing Institute Co-founder, MediaGamma Ltd. |
I am looking for a few postdoctoral researchers on Reinforcement Learning, Multiagent Learning and their applications on search and recommendation. If interested, please contact me.
Research Interests
AI and Machine Learning, (Multi-agent) Reinforcement Learning and Control, 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
Explainable AI
 |
Explanation Mining: Post Hoc Interpretability of Latent Factor Models for Recommendation Systems
|
Bayesian Learning
|
|
Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning |
Multi-agent AI
|
|
Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning |
|
|
Mean Field Multi-Agent Reinforcement Learning |
|
|
Learning to Design Games: Strategic Environments in Deep Reinforcement Learning |
|
|
An Empirical Study of AI Population Dynamics with Million-agent Reinforcement Learning |
Text/Discrete GANs
|
|
Long Text Generation via Adversarial Training with Leaked Information |
|
|
IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models |
|
|
SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient |
Neural Generative Models
|
|
Activation Maximization Generative Adversarial Nets |
|
|
A Neural Stochastic Volatility Model |
|
|
Adversarial Variational Inference for Tweedie Compound Poisson Models |
AutoML
|
|
Reinforcement Learning for Architecture Search by Network Transformation |
For a full list, see my Google Scholar page.
Demos
| Explanation Mining: Post Hoc Interpretability of Latent Factor Models for Recommendation Systems |
| 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 |
Books
 |
Display Advertising with Real-Time Bidding (RTB) and Behavioural Targeting |
 |
Dynamic Information Retrieval Modeling |