← Back
Computation

Reinforcement Learning from Interactive Theorem Prover Feedback

Close the loop between AI and human-guided interactive theorem provers by using reinforcement learning to refine proofs based on feedback from proof assistants.

Resources (9)

Advancing open-source AI for math
Initiative
AI achieves silver-medal standard solving International Mathematical Olympiad problems
Initiative
FrontierMath A math benchmark testing the limits of AI
Initiative
AI for Math Fund
Funding Program
Future Program: Exponentiating Mathematics
Funding Program
Automating Math by Adam Marblestone
Whitepapers and Essays
Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learning
Whitepapers and Essays
Harmonic
Company
LEAN: Developing a dependently typed programming language and proof assistant
FRO

R&D Gaps (1)

Proving Math Theorems is Challenging for Both Humans and AI

Computation
Both human mathematicians and current AI systems struggle with proving complex math theorems. Enhancing theorem proving through interactive and automated methods could push the boundaries of mathematical reasoning.
Computation
50