Xiangyu Zhao
Xiangyu Zhao
Home
Publications
Projects
Talks
Notes
CV
Light
Dark
Automatic
TensorFlow
Towards a Competitive 3-Player Mahjong AI using Deep Reinforcement Learning
Presented at the 2022 IEEE Conference on Games (CoG).
24 Aug 2022 6:50 PM — 7:00 PM
Virtual
Xiangyu Zhao
,
Sean B. Holden
Towards a Competitive 3-Player Mahjong AI using Deep Reinforcement Learning
Published at the 2022 IEEE Conference on Games (CoG).
Xiangyu Zhao
,
Sean B. Holden
Building a 3-Player Mahjong AI using Deep Reinforcement Learning
We present Meowjong, an AI for 3-player Mahjong (Sanma) using deep reinforcement learning. We define an informative and compact 2-dimensional data structure for encoding the observable information in a Sanma game. We pre-train 5 CNNs for Sanma’s 5 actions, and enhance the major action’s model via self-play RL using the Monte Carlo policy gradient method.
Xiangyu Zhao
,
Sean B. Holden
A Neural Network Approach to Named Entity Recognition on Noisy User-Generated Texts
MEng Natural Language Processing Final Assignment.
Xiangyu Zhao
3 Dec 2021
A Neural Network Approach to Named Entity Recognition on Noisy User-Generated Texts
MEng Natural Language Processing Final Assignment.
Xiangyu Zhao
Deep Reinforcement Learning for Mahjong
Bachelor’s Dissertation supervised by
Dr Sean Holden
.
Xiangyu Zhao
,
Sean B. Holden
14 May 2021
Deep Reinforcement Learning for Mahjong
Bachelor’s Dissertation supervised by
Dr Sean Holden
.
Xiangyu Zhao
,
Sean B. Holden
Analysing Clickstream Data for Online Shopping
Undergraduate Third Year Data Science Final Practical.
Xiangyu Zhao
3 Dec 2020
Analysing Clickstream Data for Online Shopping
Undergraduate Third Year Data Science Final Practical.
Xiangyu Zhao
Cite
×