I’m exploring biologically inspired, self-organizing systems and open-ended learning — interested in creating artificial life capable of lifelong learning, and autonomous exploration.
Highlighted AI/ML projects:
| Project | Description | Info |
|---|---|---|
| OMNI-X | Minimal interface and a collection of composable building blocks for running the OMNI-EPIC algorithm on any domain. | 🚧🔜 |
| NEAT | NEAT algorithm in pure python | ✅ |
| LNDP | PyTorch paper replica of Evolving Self-Assembling Neural Networks: From Spontaneous Activity to Experience-Dependent Learning | ☑️ |
| multi-agent-transformer | Explorations into Multi-Agent Reinforcement Learning is a Sequence Modeling Problem | ☑️ |
| es-torch | A lightweight PyTorch implementation of OpenAI-ES, combined with a custom distributed training orchestrator. | ✅ |
Other code/projects:
| Project | Description | Info |
|---|---|---|
| dotfiles | Config files, utility scripts, ... |     |
| Obsidian Homepage | Personal-stats visualization from Obsidian daily-note metadata |    |
| aleator | RNG-based habit formation app. |      |
| Sentinel-2 Landcover Classification | (Diploma Project) Landcover classification on sentinel-2 data with Prithvi, EfficientNet-Unet and OSM / CNES Landcover labels. |     GeoJSON |
| TruthTabler | Boolean expression parser, simplifier, converter. | |
| 2048JavaFx-Bot | 2048-Game in JavaFx, including a parallel expectimax bot which gets to 4096 most of the time. |  |