Zero-training entropy agent beats DeepMind's trained RL on Melting Pot social dilemmas. 350 lines of NumPy, no neural networks, no reward. DOI: 10.5281/zenodo.18717202
-
Updated
Feb 22, 2026 - Python
Zero-training entropy agent beats DeepMind's trained RL on Melting Pot social dilemmas. 350 lines of NumPy, no neural networks, no reward. DOI: 10.5281/zenodo.18717202
Unsupervised real-time network intrusion detection system using WFDS for zero-training attack detection with sliding window analysis and confidence-based thresholding.
📰 TF-IDF News Classifier: Zero-training, pure-Python tool that uses TF-IDF + cosine similarity to instantly tag articles by your custom keyword-based categories.
Zero-training POCs measuring where a frozen local embedder earns its keep — one model, four endpoint jobs (log/command anomaly, routing, entity resolution) on real data with pre-registered verdicts.
Add a description, image, and links to the zero-training topic page so that developers can more easily learn about it.
To associate your repository with the zero-training topic, visit your repo's landing page and select "manage topics."