tart All work

PERSONAL / CREATURE LAB

Creature Lab

One fruit fly. Three experimental worlds: a 3D terrain playground, a neural maze, and a Pac-Man arena that learns from rewards.

Personal side project · Simulation & learning

My contribution

Built a unified light/dark hub, 3D replay and terrain controls, neural telemetry, an arcade-inspired ghost engine, and a reward-trained motor readout with paired evaluation.

Download CV (English)

Try it · mini version

See what it can do

Creature Lab home page with green styling and three experiment cards
Creature Lab home page: a shared hub for body physics, neural navigation, and reward learning.

Personal side project · Fly training, physics & neural simulation

What this project does

Creature Lab brings three fruit-fly experiments into one responsive home: a 3D walking world, a FlyWire neural maze, and Fly Pac-Man. A shared green theme connects light and dark modes, fullscreen viewers, replay controls, and visible evidence.

Inside the project

  • Explore the 3D terrain lab with orbit, middle-drag pan, zoom, editable ramps and recorded MuJoCo movement.
  • Compare recorded neural-maze behavior with intact wiring, disconnected edges, silenced descending output and untrained controls.
  • Train an artificial Pac-Man motor readout through rewards. After 20,000 additional training games, the validation-selected checkpoint improved from 60/200 to 97/200 wins on the same fresh test games: 30% to 48.5%.
  • Use the public showcase for recordings; run the Python gateway for live keyboard play, fresh ghost seeds and optional training through a configured tailnet server.

Skills & practical experience

Practice connecting scientific simulation to an accessible interface, implementing reproducible game logic, evaluating continued learning on paired tests, and documenting the boundary between measured anatomy and engineered control.

Three.jsPythonFlyWireReward learningMuJoCoData visualizationResponsive UI

The gallery contains actual interface captures. The 19-second tour combines those captures with recorded body-physics footage. The 30% and 48.5% results compare two trained readouts on the same 200 seeds; only the readout learns, and these are simulated experiments rather than a living fly brain.

Project context

Measured FlyWire connectivity is used in computer simulations. Anatomical wiring stays fixed; an artificial motor readout learns. The public showcase plays saved experiments, while the local Python app supports live Pac-Man and optional tailnet training.

Project media

3D terrain playground with recorded body physics and neural telemetry
01 · The walking world — orbit, pan, edit terrain and replay calculated NeuroMechFly movement.
Neural maze with ten courses and causal controls
02 · A way through — recorded FlyWire neural decisions and controls that silence or disconnect the signal.
Fly Pac-Man arena with four ghosts, rewards and evaluation results
03 · Fly Pac-Man — a fruit-fly player, distinct ghost targets and a trained motor readout.
Creature Lab home page in dark green mode
A consistent green palette in both light and dark mode.
19-second visual tour: interface screenshots combined with an actual recorded 3D physics replay. Neural-maze and arcade sections are still-image previews.