Biomedical Engineering student at the University of Florida (Honors, Class of 2030), interested in mechanical systems and controls. Reinforcement learning, cryptanalysis, and whatever the next project demands. Started programming June 2026. Documentation, source papers, and existing repositories for research; AI tools leveraged as a tutor and assistant for unfamiliar topics.
- mujoco-gripper-rl — TD3 reinforcement learning agent hand-implemented for custom robotics environment in MuJoCo
- td3-validation — TD3 architecture validated against known, well-documented Gymnasium-based benchmark
- blackjack-ml — Tabular Q-learning agent for object-oriented casino-style Blackjack environment
- blackjack-table — Human-playable implementation of the Blackjack engine above
- vigenere-decoder — Vigenere cipher decoder (Kasiski examination, Index of Coincidence) for CTF cryptanalysis
- markov-generation — Terminal-based Markov chain text generator
- maze-algorithms — Algorithmic maze generation and pathfinding with Pygame visualization
- pidkit — A minimal, dependency-free PID controller package for Python
- pid-plants — Plant testbed for pidkit validation against dynamic simulations
- Languages: Python, JavaScript, CSS, HTML
- Environment: Git, uv
- Machine Learning & Simulation: PyTorch, MuJoCo, Gymnasium, NumPy
- Interface: Flask, Pygame