Project Snapshot
- Title: PALEO (with Primal Mind)
- Team: World's Finest
- Members: Laura Wetherhold, Alexus Aguirre Arias
- Target: Dinosaur survival agent with interpretable thought/action loops.
Complete web version of the check-in response, with current experiment artifacts experiment artifacts and upcoming technical deliverables.
COMPLETE Core written check-in content is now published here.
DONEScaffold, docs, deployment, Serengeti training, and PoT fine-tuning are ready.
IN PROGRESSLetta-in-the-loop integration and full in-game smoke testing are next.
This page now reflects the later project state, including saved model metrics and figures.
Project title: PALEO (with Primal Mind)
Team: World's Finest (Laura Wetherhold, Alexus Aguirre Arias)
PALEO addresses a common issue in game AI: predictable and non-interpretable NPC behavior. The system uses computer vision plus behavior modeling to infer high-level state (threat, urgency, risk posture), then generates explainable thought logs and aligned actions.
Current repo status has moved past scaffold-first: src/, scripts/, tests/,
docs/, saved checkpoints, saved metrics, reproducible commands in README, and Pages deployment.
These cards summarize the current outputs and next artifact upgrades.
Now populated by convergence curves from the latest ResNet-18 sweep.
Now represented with learning-rate sensitivity across augmented runs.
Now represented with final comparison across baseline and model variants.
Placeholder for success/failure behavior examples and short analyses.
Placeholder for per-dinosaur memory state view (needs, threat memory, actions).
Placeholder for in-engine clips showing perceive-decide-act behavior loop.
Best selected run: ResNet-18, lr=1e-4, augmentation on, 15 epochs.
| Run | Notes |
|---|---|
| LR=1e-3 (aug) | Stronger early gains, less stable at later epochs. |
| LR=1e-4 (aug) | More stable convergence and selected as best configuration. |
Baseline versus model variants from the latest sweep.