English
Related papers

Related papers: Learning Search-Space Specific Heuristics Using Ne…

200 papers

This paper presents a new framework for anytime heuristic search where the task is to achieve as many goals as possible within the allocated resources. We show the inadequacy of traditional distance-estimation heuristics for tasks of this…

Artificial Intelligence · Computer Science 2015-03-19 D. Davidov , S. Markovitch

Recent advances in reinforcement learning (RL) have led to a growing interest in applying RL to classical planning domains or applying classical planning methods to some complex RL domains. However, the long-horizon goal-based problems…

Artificial Intelligence · Computer Science 2022-03-08 Clement Gehring , Masataro Asai , Rohan Chitnis , Tom Silver , Leslie Pack Kaelbling , Shirin Sohrabi , Michael Katz

A key challenge in satisficing planning is to use multiple heuristics within one heuristic search. An aggregation of multiple heuristic estimates, for example by taking the maximum, has the disadvantage that bad estimates of a single…

Artificial Intelligence · Computer Science 2021-04-13 David Speck , André Biedenkapp , Frank Hutter , Robert Mattmüller , Marius Lindauer

In recent years, there has been growing interest in utilizing modern machine learning techniques to learn heuristic functions for forward search algorithms. Despite this, there has been little theoretical understanding of what they should…

Artificial Intelligence · Computer Science 2025-01-07 Carlos Núñez-Molina , Masataro Asai , Pablo Mesejo , Juan Fernández-Olivares

Deep learning uses neural networks which are parameterised by their weights. The neural networks are usually trained by tuning the weights to directly minimise a given loss function. In this paper we propose to re-parameterise the weights…

Neural and Evolutionary Computing · Computer Science 2022-03-14 Michael Fairbank , Spyridon Samothrakis , Luca Citi

Recent work investigated the use of Reinforcement Learning (RL) for the synthesis of heuristic guidance to improve the performance of temporal planners when a domain is fixed and a set of training problems (not plans) is given. The idea is…

Artificial Intelligence · Computer Science 2025-05-20 Irene Brugnara , Alessandro Valentini , Andrea Micheli

Domain-independent planning is one of the foundational areas in the field of Artificial Intelligence. A description of a planning task consists of an initial world state, a goal, and a set of actions for modifying the world state. The…

Artificial Intelligence · Computer Science 2014-01-24 Carmel Domshlak , Erez Karpas , Shaul Markovitch

In spite of the recent improvements in the performance of the solvers based on the DPLL procedure, it is still possible for the search algorithm to focus on the wrong areas of the search space, preventing the solver from returning a…

Artificial Intelligence · Computer Science 2015-03-18 Marcello Balduccini

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 investigate the automated…

Artificial Intelligence · Computer Science 2019-03-11 Thiago Freitas dos Santos , Paulo E. Santos , Leonardo A. Ferreira , Reinaldo A. C. Bianchi , Pedro Cabalar

We present three novel graph representations of planning tasks suitable for learning domain-independent heuristics using Graph Neural Networks (GNNs) to guide search. In particular, to mitigate the issues caused by large grounded GNNs we…

Artificial Intelligence · Computer Science 2024-10-29 Dillon Z. Chen , Sylvie Thiébaux , Felipe Trevizan

Autonomous exploration of unknown environments is a vital function for robots and has applications in a wide variety of scenarios. Our focus primarily lies in its application for the task of efficient coverage of unknown environments.…

Robotics · Computer Science 2021-08-27 Arsh Tangri , Dhruv Joshi , Ashalatha Nayak

Heuristic forward search is currently the dominant paradigm in classical planning. Forward search algorithms typically rely on a single, relatively simple variation of best-first search and remain fixed throughout the process of solving a…

Artificial Intelligence · Computer Science 2019-11-28 Pawel Gomoluch , Dalal Alrajeh , Alessandra Russo , Antonio Bucchiarone

We demonstrate that a single training trajectory can transform a graph neural network into an unsupervised heuristic for combinatorial optimization. Focusing on the Travelling Salesman Problem, we show that encoding global structural…

Artificial Intelligence · Computer Science 2026-02-03 Yimeng Min , Carla P. Gomes

Path finding in graphs is one of the most studied classes of problems in computer science. In this context, search algorithms are often extended with heuristics for a more efficient search of target nodes. In this work we combine recent…

Artificial Intelligence · Computer Science 2022-04-20 Danilo Numeroso , Davide Bacciu , Petar Veličković

Computing goal-directed behavior is essential to designing efficient AI systems. Due to the computational complexity of planning, current approaches rely primarily upon hand-coded symbolic action models and hand-coded heuristic-function…

Machine Learning · Computer Science 2020-10-21 Rushang Karia , Siddharth Srivastava

The performance of search algorithms for grid-based pathfinding, e.g. A*, critically depends on the heuristic function that is used to focus the search. Recent studies have shown that informed heuristics that take the positions/shapes of…

Machine Learning · Computer Science 2026-03-02 Aleksandr Ananikian , Daniil Drozdov , Konstantin Yakovlev

We achieved a new milestone in the difficult task of enabling agents to learn about their environment autonomously. Our neuro-symbolic architecture is trained end-to-end to produce a succinct and effective discrete state transition model…

Artificial Intelligence · Computer Science 2020-08-13 Masataro Asai , Christian Muise

Link prediction is a key problem for network-structured data. Link prediction heuristics use some score functions, such as common neighbors and Katz index, to measure the likelihood of links. They have obtained wide practical uses due to…

Machine Learning · Computer Science 2018-11-21 Muhan Zhang , Yixin Chen

We explore unique considerations involved in fitting ML models to data with very high precision, as is often required for science applications. We empirically compare various function approximation methods and study how they scale with…

Machine Learning · Computer Science 2023-02-01 Eric J. Michaud , Ziming Liu , Max Tegmark

In this paper, we describe the hyper-parameter search problem in the field of machine learning and present a heuristic approach in an attempt to tackle it. In most learning algorithms, a set of hyper-parameters must be determined before…

Machine Learning · Computer Science 2020-01-14 Wei Hao Khoong