DeepMind’s latest: An AI for handling mathematical proofs

Just like AlphaZero, AlphaProof in most cases used two main components. The first was a huge neural net with a few billion parameters that learned to work in the Lean environment through trial and error. It was rewarded for each proven or disproven statement and penalized for each reasoning step it took, which was a way of incentivizing short, elegant proofs.

It was also trained to use a second component, which was a tree search algorithm. This explored all possible actions that…