Hi! I'm an engineer and researcher passionate about Reinforcement Learning (RL). I hold a PhD from the University of Auckland in RL and have several years of experience in Python, PyTorch, and deep learning.

My work focuses on bridging the gap between theoretical RL and real-world applications. I develop open-source tools to make RL more accessible, from algorithms to documentation, ensuring researchers and developers can easily apply RL in practical experiments.

🌟 Current Project: ReinforceUI Studio
The biggest project you can support right now is ReinforceUI Studio—a Python-based application that simplifies RL training configuration and monitoring. Its intuitive GUI eliminates the need for extra repositories or complex command lines, making RL workflows more efficient and user-friendly.

🚀 Why Use ReinforceUI Studio?
✅ Simplified RL Workflows – No complex command-line operations, just an intuitive GUI.
✅ Seamless Environment Support – Works with MuJoCo, OpenAI Gymnasium, and DeepMind Control Suite.
✅ Algorithm Customization – Adjust hyperparameters and algorithms or use optimized defaults.
✅ Real-Time Monitoring – Track training progress, metrics, and performance curves live.
✅ Comprehensive Data Logging – Automatically save training results, plots, models, and videos.
✅ User-Friendly Training & Testing – Train, evaluate, and refine RL policies effortlessly.

By sponsoring me, you directly contribute to the development of open-source RL tools like ReinforceUI Studio—keeping them free and accessible for all! 🚀