Projects

Bachelor thesis: can reinforcement learning improve a VLA policy after fine-tuning?

A quadruped on an ESP32-CAM, with a learned policy correcting the hand-written gait.

A locomotion policy trained in simulation, running on the microcontroller itself.

An alien friend that dances to your music.

A desktop operating system UX living inside a browser tab.

3D interactive visualization of neural network architectures.

The battle of the Tetris AIs — deep Q-network against a genetic algorithm.

The bird is a window. So are the pipes.