Learning to Select Goals in Automated Planning with Deep-Q Learning

Autor: Núñez-Molina, Carlos, Fernández-Olivares, Juan, Pérez, Raúl

Publikováno v: N\'u\~nez-Molina, C., Fern\'andez-Olivares, J., & P\'erez, R. (2022). Learning to select goals in Automated Planning with Deep-Q Learning. Expert Systems with Applications, 202, 117265

In this work we propose a planning and acting architecture endowed with a module which learns to select subgoals with Deep Q-Learning. This allows us to decrease the load of a planner when faced with scenarios with real-time restrictions. We have tra

Externí odkaz: http://arxiv.org/abs/2406.14779

On Using Admissible Bounds for Learning Forward Search Heuristics

Autor: Núñez-Molina, Carlos, Asai, Masataro, Mesejo, Pablo, Fernández-Olivares, Juan

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 learn, how

Externí odkaz: http://arxiv.org/abs/2308.11905

A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making

Autor: Núñez-Molina, Carlos, Mesejo, Pablo, Fernández-Olivares, Juan

Publikováno v: Carlos N\'u\~nez Molina, Pablo Mesejo, & Juan Fern\'andez-Olivares. (2024). A review of symbolic, subsymbolic and hybrid methods for sequential decision making. ACM Computing Surveys, 56(11), Article 272, 1-36

In the field of Sequential Decision Making (SDM), two paradigms have historically vied for supremacy: Automated Planning (AP) and Reinforcement Learning (RL). In the spirit of reconciliation, this article reviews AP, RL and hybrid methods (e.g., nove

Externí odkaz: http://arxiv.org/abs/2304.10590

NeSIG: A Neuro-Symbolic Method for Learning to Generate Planning Problems

Autor: Núñez-Molina, Carlos, Mesejo, Pablo, Fernández-Olivares, Juan

In the field of Automated Planning there is often the need for a set of planning problems from a particular domain, e.g., to be used as training data for Machine Learning or as benchmarks in planning competitions. In most cases, these problems are cr

Externí odkaz: http://arxiv.org/abs/2301.10280

Mortalidad evitable: el caso de la frontera norte de México, 1980-1990

Autor: Molina Carlos Antonio G., López Maria Victoria L.

Publikováno v: Cadernos de Saúde Pública, Vol 11, Iss 3, Pp 395-407 (1995)

Cuando se conciben las causas de muerte como el resultado de procesos mórbidos que pudieron haber sido evitados con distintos tipos de medidas económicas, sociales, de servicios de salud y los avances en el conocimiento científico y tecnológico,

Externí odkaz: https://doaj.org/article/a74c07e5a3a44ac3a9324fdd5e32768a