- Blog
- CV generator
- Community
- Documentation
Jianhong Wang
London, United Kingdom
My interests lie in Bayesian Learning, Multi-agent Learning, Reinforcement Learning, Task-oriented Dialogue Systems and Multi-agent Reinforcement Learning for Power Systems.
CodersRank Score
What is this?
This represents your current experience. It calculates by analyzing your connected repositories. By measuring your skills by your code, we are creating the ranking, so you can know how good are you comparing to another developers and what you have to improve to be better
Information on how to increase score and ranking details you can find in this blog post.
179.2
CodersRank Rank
Top 4%
Top 100
Jupyter Notebook
Developer
United Kingdom
Top 100
Python
Developer
United Kingdom
Highest experience points: 0 points,
0 activities in the last year
Python
152.1
exp.
Jupyter Notebook
8.1
exp.
Shell
7.4
exp.
MATLAB
5.9
exp.
List your work history, including any contracts or internships
Huawei Technologies Research & Development (UK) Ltd
Nov 2020 - Mar 2021 (4 months)
Part-time Research Internship at London Research Center (Noah's Ark Lab)
Braintree ~ nature of intelligence
May 2019 - Sep 2019 (4 months)
Part-time Research Engineer Internship
This section lets you add any degrees or diplomas you have earned.
Imperial College London
Doctor of Philosophy - PhD, Machine Learning for Complex Networks
Jan 2019 - Jan 2023
Interests:
Reinforcement Learning
Multi-agent Learning
Game Theory
Task-oriented Dialogue System
Multi-agent Reinforcement Learning for Active Voltage Control in Power System
Current Research:
1. Shapley Q-value: A Local Reward Approach to Solve Global Reward Games, accepted by AAAI 2020 (Oral).
2. Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System, accepted by ICLR 2021 (Poster).
3. Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks, accepted by NeurIPS 2021 (Poster)
Reinforcement Learning
Multi-agent Learning
Game Theory
Task-oriented Dialogue System
Multi-agent Reinforcement Learning for Active Voltage Control in Power System
Current Research:
1. Shapley Q-value: A Local Reward Approach to Solve Global Reward Games, accepted by AAAI 2020 (Oral).
2. Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System, accepted by ICLR 2021 (Poster).
3. Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks, accepted by NeurIPS 2021 (Poster)
University College London
Master of Research (MRes), Web Science and Big Data Analytics
Jan 2017 - Jan 2018
Research:
1. Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning, accepted by NeurIPS 2018 (Poster).
2. Mean-field Fictitous Play on Potential Game.
Interests:
Game Theory
Optimization
Reinforcement Learning
Courses Learned:
Statistical Natural Language Processing
Probabilistic and Unsupervised Learning (Taught by Gatsby Unit)
Numerical Optimization
Advanced Deep Learning and Reinforcement Learning (Taught by Google DeepMind)
1. Thermostat-assisted continuously-tempered Hamiltonian Monte Carlo for Bayesian learning, accepted by NeurIPS 2018 (Poster).
2. Mean-field Fictitous Play on Potential Game.
Interests:
Game Theory
Optimization
Reinforcement Learning
Courses Learned:
Statistical Natural Language Processing
Probabilistic and Unsupervised Learning (Taught by Gatsby Unit)
Numerical Optimization
Advanced Deep Learning and Reinforcement Learning (Taught by Google DeepMind)
Imperial College London
Master of Science (MSc), Computing (Machine Learning)
Jan 2016 - Jan 2017
I mainly study generative model (graphical model) during master course.
Courses Learned:
CO-343 Operations Research (Linear Optimization)
CO-304 Logic Based Learning
CO-421H Computational Neural Dynamics
CO-424H Learning in Autonomous System (Reinforcement Learning)
CO-477 Computational Optimization (Non-linear Optimization)
CO-433 Advanced Robotics
CO-496 Mathematics for Machine Learning and Probabilistic Inference (Required Mathematical Knowledge of Machine Learning)
CO-495 Advanced Machine Learning and Pattern Recognition (EM for Graphical Model)
CO-493 Data Analysis and Probabilistic Inference (Bayesian Networks, Gaussian Process and MCMC)
CO-512 Independent Study Option (A short term research on GAN and its variants)
Individual Project:
My Individual Project is about how to detect snore sounds in time-frequency images into four categories by End-to-End Model.
The difficulties:
1) The dataset of small size
2) The ambiguities among four categories of snore sounds
Courses Learned:
CO-343 Operations Research (Linear Optimization)
CO-304 Logic Based Learning
CO-421H Computational Neural Dynamics
CO-424H Learning in Autonomous System (Reinforcement Learning)
CO-477 Computational Optimization (Non-linear Optimization)
CO-433 Advanced Robotics
CO-496 Mathematics for Machine Learning and Probabilistic Inference (Required Mathematical Knowledge of Machine Learning)
CO-495 Advanced Machine Learning and Pattern Recognition (EM for Graphical Model)
CO-493 Data Analysis and Probabilistic Inference (Bayesian Networks, Gaussian Process and MCMC)
CO-512 Independent Study Option (A short term research on GAN and its variants)
Individual Project:
My Individual Project is about how to detect snore sounds in time-frequency images into four categories by End-to-End Model.
The difficulties:
1) The dataset of small size
2) The ambiguities among four categories of snore sounds
University of Liverpool
Bachelor of Engineering - BE, Computer Science and Electronic Engineering
Jan 2012 - Jan 2016
Shanghai Jincai High School (上海进才中学)
Jan 2009 - Jan 2012
Text Mining and Analytics
Jul 2015