Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices
We introduce algebraic machine reasoning, a new reasoning framework that is well-suited
for abstract reasoning. Effectively, algebraic machine reasoning reduces the difficult process …
for abstract reasoning. Effectively, algebraic machine reasoning reduces the difficult process …
Proving theorems using incremental learning and hindsight experience replay
Traditional automated theorem proving systems for first-order logic depend on speed-
optimized search and many handcrafted heuristics designed to work over a wide range of …
optimized search and many handcrafted heuristics designed to work over a wide range of …
A Survey on Deep Learning for Theorem Proving
Theorem proving is a fundamental aspect of mathematics, spanning from informal reasoning
in mathematical language to rigorous derivations in formal systems. In recent years, the …
in mathematical language to rigorous derivations in formal systems. In recent years, the …
[PDF][PDF] Lemmas: Generation, selection, application
Noting that lemmas are a key feature of mathematics, we engage in an investigation of the
role of lemmas in automated theorem proving. The paper describes experiments with a …
role of lemmas in automated theorem proving. The paper describes experiments with a …
Fully reusing clause deduction algorithm based on standard contradiction separation rule
An automated theorem proving (ATP) system's capacity for reasoning is significantly
influenced by the inference rules it uses. The recently introduced standard contradiction …
influenced by the inference rules it uses. The recently introduced standard contradiction …
An ensemble approach for automated theorem proving based on efficient name invariant graph neural representations
Using reinforcement learning for automated theorem proving has recently received much
attention. Current approaches use representations of logical statements that often rely on the …
attention. Current approaches use representations of logical statements that often rely on the …
gym-saturation: Gymnasium Environments for Saturation Provers (System description)
B Shminke - … Conference on Automated Reasoning with Analytic …, 2023 - Springer
This work describes a new version of a previously published Python package—gym-
saturation: a collection of OpenAI Gym environments for guiding saturation-style provers …
saturation: a collection of OpenAI Gym environments for guiding saturation-style provers …
Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks
Neurosymbolic AI combines the interpretability, parsimony, and explicit reasoning of
classical symbolic approaches with the statistical learning of data-driven neural approaches …
classical symbolic approaches with the statistical learning of data-driven neural approaches …
gym-saturation: an OpenAI Gym environment for saturation provers
B Shminke - arXiv preprint arXiv:2203.04699, 2022 - arxiv.org
gym-saturationis an OpenAI Gym environment for reinforcement learning (RL) agents
capable of proving theorems. Currently, only theorems written in a formal language of the …
capable of proving theorems. Currently, only theorems written in a formal language of the …
[PDF][PDF] Reinforcement Learning for Guiding the E Theorem Prover
J McKeown, G Sutcliffe - The International FLAIRS Conference …, 2023 - journals.flvc.org
Abstract Automated Theorem Proving (ATP) systems search for a proof in a rapidly growing
space of possibilities. Heuristics have a profound impact on search, and ATP systems make …
space of possibilities. Heuristics have a profound impact on search, and ATP systems make …