| Machine Learning | 61 |
|---|---|
| Computer Vision | 48 |
| Data Science | 0 |
| NLP & LLMs | 0 |
| AI Agents | 58 |
| MLOps | 11 |
Each node is one domain, scored only from evidence in these public repositories. Select one to see why.
Substantial implementations with real depth.
3 public repositories → 2 with AI work, evaluated. The other 1 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected
Ordered by how much each project adds to the Atlas score, not by its own score. A project with evidence in several domains can rank above one with a slightly higher project score. Choose a domain to focus on the projects with meaningful evidence there.
63% of Atlas Score
EmblaV2 is a reinforcement learning agent based on DreamerV3 with added intrinsic motivation and self-model components, trained on various Gymnasium environments using PyTorch.
37% of Atlas Score
EmblaV1 extends the DreamerV3 reinforcement learning agent with a Feature-Fused Kinematic State Model (FFKSM) to enhance morphology awareness. The implementation integrates a self-model component trained on rendered images and evaluates its effectiveness on various MuJoCo environments.
