Paper
HackingFace
An open-source reinforcement learning environment project that organizes formalized data into a dataset containing 369 tasks and 405 mathematics problems. It includes an automated Linux grader and can verify model proofs.
Timeline (last 90 days)
Oct 13
The HackingFace project compiles the formalized data recently released by OpenAI into an open-source reinforcement learning environment containing 369 tasks and 405 math problems, equipped with a Linux automatic scorer.
Unverified50%