tesserack

tesserack

Compiling strategy guides into reward functions for reinforcement learning. Uses Claude Vision to ex

33

GitHub Stars

Jan 23, 2026

Launch Date

6h ago

First Tracked

About

AI Summary

Tesserack is an AI tool that compiles strategy guides into reward functions for reinforcement learning by utilizing Claude Vision to extract unit tests from game guides, enabling the training of agents with dense and interpretable rewards.

Compiling strategy guides into reward functions for reinforcement learning. Uses Claude Vision to extract unit tests from game guides, then trains agents with dense, interpretable rewards.

Tags

browser-game
claude
gameboy
llms
machine-learning
neural-network
pokemon
reinforcement-learning
reward-shaping
rl
tensorflow-js
webgpu
JavaScript