Learning Heuristics for Automated Reasoning through Reinforcement Learning

2019-05-01 · ICLR 2019 5 · Gil Lederman, Markus N. Rabe, Edward A. Lee, Sanjit A. Seshia

We demonstrate how to learn efficient heuristics for automated reasoning algorithms through deep reinforcement learning. We focus on backtracking search algorithms for quantified Boolean logics, which already can solve formulas of impressive size - up to 100s of thousands of variables. The main challenge is to find a representation of these formulas that lends itself to making predictions in a scalable way. For challenging problems, the heuristic learned through our approach reduces execution time by a factor of 10 compared to the existing handwritten heuristics.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Learning Heuristics for Quantified Boolean Formulas through Reinforcement Learning

2020-05-01 · ICLR 2020 1 · Gil Lederman, Markus Rabe, Sanjit Seshia, Edward A. Lee

We demonstrate how to learn efficient heuristics for automated reasoning algorithms for quantified Boolean formulas through deep reinforcement learning. We focus on a backtracking search algorithm, which can already solv…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Learning Heuristics for Quantified Boolean Formulas through Deep Reinforcement Learning

2018-07-20 · Gil Lederman, Markus N. Rabe, Edward A. Lee, Sanjit A. Seshia

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

A Deep Reinforcement Learning Approach to First-Order Logic Theorem Proving

2019-11-05 · Maxwell Crouse, Ibrahim Abdelaziz, Bassem Makni, Spencer Whitehead 외

Automated theorem provers have traditionally relied on manually tuned heuristics to guide how they perform proof search. Deep reinforcement learning has been proposed as a way to obviate the need for such heuristics, how…

Automated Theorem Proving Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving LLMs

2026-01-28 · Oguzhan Gungordu, Siheng Xiong, Faramarz Fekri arxiv

Large Language Models (LLMs) have enabled automated heuristic design (AHD) for combinatorial optimization problems (COPs), but existing frameworks' reliance on fixed evolutionary rules and static prompt templates often l…

Heuristics, Answer Set Programming and Markov Decision Process for Solving a Set of Spatial Puzzles

2019-02-16 · Thiago Freitas dos Santos, Paulo E. Santos, Leonardo A. Ferreira, Reinaldo A. C. Bianchi 외

Spatial puzzles composed of rigid objects, flexible strings and holes offer interesting domains for reasoning about spatial entities that are common in the human daily-life's activities. The goal of this work is to inves…

Q-Learning Reinforcement Learning Reinforcement Learning (RL)