#lean

[ follow ]
fromwww.nature.com
1 week ago
Artificial intelligence

Olympiad-level formal mathematical reasoning with reinforcement learning

AlphaProof is an AlphaZero-inspired reinforcement-learning agent that learns rigorous formal mathematical reasoning and proof construction within the Lean interactive theorem-proving environment.
fromPythontest
3 weeks ago

Announcing the Lean TDD book | PythonTest

So far I have: a first draft of the introduction chapter written an outline of the chapters I want to write and for some chapters, some subtopics I want to cover a book landing page a process for building the book a deployment system a way to notify readers of book updates a quick canva-built cover And now I'm ready to hop back to writing. I'm confident all the gears are in place.
Software development
[ Load more ]