- 👋 Hi, I’m Winsor Tse
- 👀 Software Developer/ MLE/ DRL
- 📫 How to reach me tsewinsor@gmail.com
- This is my personal website:(https://winsor-portfolio.vercel.app/)
View winsor-tse's full-sized avatar
🏠
Working from home
Winsor Tse winsor-tse
🏠
Working from home
I do SoTA Deep Reinforcement Learning, Machine Learning, Software Engineering. Follow Me.
Pinned Loading
-
MinecraftModdingFiles
MinecraftModdingFiles PublicUses the Minecraft IntelliJ IDE. Custom items, weapons, blocks, etc.
Java
-
RL-Decision-Server
RL-Decision-Server PublicTraining and evaluating DRL agents for Yugen Saga via a custom environment and bridge
Python 3
-
Reinforcement_Learning_Notes
Reinforcement_Learning_Notes PublicBased on OMSCS CS7642: Reinforcement Learning, Also adding upon my ideas and knowledge.
Jupyter Notebook 3
-
HHMARL_AirCombat
HHMARL_AirCombat PublicForked from IDSIA-papers/HHMARL_AirCombat
Heterogeneous Hierarchical Multi Agent Reinforcement Learning for Realistic Air Combat
Python
-
PPO_LSTM
PPO_LSTM PublicCustom PPO-LSTM implementation inspired by Ray RLlib’s recurrent PPO and written in a CleanRL-style training loop for non-CNN Gymnasium environments with vector observations. The project targets MD...
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.