ML Application · JavaScript

rl-livive-net

Jarad Peckenpaugh@jpeckenpaugh · Atlas 69.9 · #4= builder

View on GitHub Open Jarad Peckenpaugh's Atlas

What it is

rl-livive-net is an interactive LunarLander application that allows users to play solo, co-pilot with AI policies, or compete in multiplayer matches using 9 pre-trained ONNX policies. It includes tools for exporting RL models to ONNX and generating retro arcade voice lines, delivering a complete end-to-end experience.

Scored from the code at its last scan, 18 Oct 2026. How merit is scored

Where it counts

Machine Learning85%
AI Agents30%
NLP & LLMs15%
Data Science10%
Computer Vision5%
MLOps5%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

Around it on the Machine Learning board

Whole board

RankProjectBuilderFieldMerit

18, shared rankandrej-karpathy-full-courseEducational Implementation · Jupyter NotebookThe repository contains a series of Jupyter notebooks and Python scripts that walk through building neural networks from basic bigram models up to a GPT-2 replica, following Andrej Karpathy's Neural Networks: Zero to Hero course.58.6/100AdvancedPop AlexandruMachine Learning
18, shared rankneural-style-transfer-cnnML Application · PythonThis repository provides a PyTorch-based implementation of neural style transfer using a pretrained VGG19 model. It includes a CLI for transferring the style of one image onto another, along with unit tests and documentation.58.6/100AdvancedPop AlexandruMachine Learning
18, shared rankrl-livive-netML Application · JavaScript58.6/100AdvancedJarad PeckenpaughMachine Learning
21LeNet_5-from-scratchArchitecture Reimplementation · Jupyter NotebookThis repository provides a from-scratch PyTorch reimplementation of the LeNet-5 architecture, including a custom radial basis function output layer and loss function as described in the original paper. It includes unit tests, a training notebook, and a trained checkpoint for…57.7/100ImplementationPop AlexandruMachine Learning
22, shared rankcdeEducational Implementation · PythonThe repository presents the Compiled Domain Expertise (CDE) framework and Quantized Semantic Bottleneck Architecture (QSBA) as a specification for compiling domain expertise into deterministic instruction sets. It includes a reference implementation in the form of an Algebra…57.4/100ImplementationJarad PeckenpaughMachine Learning

What it is

Where it counts

Around it on the Machine Learning board

More from Jarad Peckenpaugh