Training Experiment · JavaScript
mines-livive-net
An in-browser retro arcade cabinet running Reinforcement Learning policies on a discrete 8x8 Minesweeper engine. Race human intuition against ONNX-exported checkpoints across training milestones with live action-masking and deterministic board seeds.
What it is
This repository provides a training and evaluation pipeline for reinforcement learning agents applied to the 8x8 Minesweeper game. It includes custom game environment, model architecture, training scripts (behavior cloning and REINFORCE), evaluation tools, and generates multiple model checkpoints with documented performance.
Where it counts
- Machine Learning80%
- AI Agents70%
- MLOps30%
- Data Science20%
- Computer Vision10%
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- 22, shared rankcdeEducational Implementation · Python57.4ImplementationJarad PeckenpaughMachine Learning
- 22, shared rankfresta-edgeML Application · Python57.4ImplementationTiago SantosMachine Learning
- 22, shared rankmines-livive-netTraining Experiment · JavaScript57.4ImplementationJarad PeckenpaughMachine Learning
- 25pcap-ml-traffic-classifierML Application · Python56.2ImplementationPop AlexandruMachine Learning
- 26bf16-update-realization-in-transformersTraining Experiment · Python55.8ImplementationRickMachine Learning
