DeepAI
Log In Sign Up

Learning Heuristics for Automated Reasoning through Deep Reinforcement Learning

07/20/2018
by   Gil Lederman, et al.
0

We demonstrate how to learn efficient heuristics for automated reasoning algorithms through deep reinforcement learning. We consider search algorithms for quantified Boolean logics, that already can solve formulas of impressive size - up to 100s of thousands of variables. The main challenge is to find a representation which lends to making predictions in a scalable way. The heuristics learned through our approach significantly improve over the handwritten heuristics for several sets of formulas.

READ FULL TEXT

page 1

page 2

page 3

page 4

11/02/2018

Automated Theorem Proving in Intuitionistic Propositional Logic by Deep Reinforcement Learning

The problem-solving in automated theorem proving (ATP) can be interprete...
10/02/2019

Improving Reasoning on DQBF

The aim of this PhD project is to develop fast and robust reasoning tool...
04/03/2020

Learning 2-opt Heuristics for the Traveling Salesman Problem via Deep Reinforcement Learning

Recent works using deep learning to solve the Traveling Salesman Problem...
03/08/2000

QUIP - A Tool for Computing Nonmonotonic Reasoning Tasks

In this paper, we outline the prototype of an automated inference tool, ...
11/09/2020

Challenges of Applying Deep Reinforcement Learning in Dynamic Dispatching

Dynamic dispatching aims to smartly allocate the right resources to the ...
06/09/2019

Neural Heterogeneous Scheduler

Access to parallel and distributed computation has enabled researchers a...
02/14/2018

From Gameplay to Symbolic Reasoning: Learning SAT Solver Heuristics in the Style of Alpha(Go) Zero

Despite the recent successes of deep neural networks in various fields s...