Reinforcement Learning

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
Towards a Competitive 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
Multi-Agent Deep Q-Learning for the Berry Poisoning Game
MEng Advanced Topics in Machine Learning Coursework.
Xiangyu Zhao
Last updated on 4 Apr 2022
Multi-Agent Deep Q-Learning for the Berry Poisoning Game
MEng Advanced Topics in Machine Learning Coursework.
Xiangyu Zhao
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
Asynchronous Methods for Deep Reinforcement Learning
Paper-reading presentation for the Reinforcement Learning topic of the MEng Advanced Topics in Machine Learning module.
11 Feb 2022 3:00 PM — 4:00 PM Computer Laboratory, University of Cambridge
Xiangyu Zhao
Asynchronous Methods for Deep Reinforcement Learning
Deep Reinforcement Learning for Mahjong
Bachelor’s Dissertation supervised by Dr Sean Holden – We present Meowjong, an AI for 3-player Mahjong (Sanma) using deep reinforcement learning, with an informative and compact 2-dimensional data structure for encoding the observable information in a Sanma game.
Xiangyu Zhao, Sean B. Holden
14 May 2021
Deep Reinforcement Learning for Mahjong
Bachelor’s Dissertation supervised by Dr Sean Holden – We present Meowjong, an AI for 3-player Mahjong (Sanma) using deep reinforcement learning, with an informative and compact 2-dimensional data structure for encoding the observable information in a Sanma game.
Xiangyu Zhao, Sean B. Holden