The Role of Entropy in Guiding a Connection Prover

by   Zsolt Zombori, et al.

In this work we study how to learn good algorithms for selecting reasoning steps in theorem proving. We explore this in the connection tableau calculus implemented by leanCoP where the partial tableau provides a clean and compact notion of a state to which a limited number of inferences can be applied. We start by incorporating a state-of-the-art learning algorithm – a graph neural network (GNN) – into the plCoP theorem prover. Then we use it to observe the system's behaviour in a reinforcement learning setting, i.e., when learning inference guidance from successful Monte-Carlo tree searches on many problems. Despite its better pattern matching capability, the GNN initially performs worse than a simpler previously used learning algorithm. We observe that the simpler algorithm is less confident, i.e., its recommendations have higher entropy. This leads us to explore how the entropy of the inference selection implemented via the neural network influences the proof search. This is related to research in human decision-making under uncertainty, and in particular the probability matching theory. Our main result shows that a proper entropy regularisation, i.e., training the GNN not to be overconfident, greatly improves plCoP's performance on a large mathematical corpus.


page 1

page 2

page 3

page 4


Reinforcement Learning of Theorem Proving

We introduce a theorem proving algorithm that uses practically no domain...

Monte Carlo Connection Prover

Monte Carlo Tree Search (MCTS) is a technique to guide search in a large...

Machine Learning Guidance and Proof Certification for Connection Tableaux

Connection calculi allow for very compact implementations of goal-direct...

Prolog Technology Reinforcement Learning Prover

We present a reinforcement learning toolkit for experiments with guiding...

Learning Theorem Proving Components

Saturation-style automated theorem provers (ATPs) based on the given cla...

Q-Learning with Differential Entropy of Q-Tables

It is well-known that information loss can occur in the classic and simp...

Please sign up or login with your details

Forgot password? Click here to reset