Guardado en:
Detalles Bibliográficos
Autores principales: Narita, Minori, Kuroiwa, Ryo, Beck, J. Christopher
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2503.16371
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908362374905856
author Narita, Minori
Kuroiwa, Ryo
Beck, J. Christopher
author_facet Narita, Minori
Kuroiwa, Ryo
Beck, J. Christopher
contents Domain-Independent Dynamic Programming (DIDP) is a state-space search paradigm based on dynamic programming for combinatorial optimization. In its current implementation, DIDP guides the search using user-defined dual bounds. Reinforcement learning (RL) is increasingly being applied to combinatorial optimization problems and shares several key structures with DP, being represented by the Bellman equation and state-based transition systems. We propose using reinforcement learning to obtain a heuristic function to guide the search in DIDP. We develop two RL-based guidance approaches: value-based guidance using Deep Q-Networks and policy-based guidance using Proximal Policy Optimization. Our experiments indicate that RL-based guidance significantly outperforms standard DIDP and problem-specific greedy heuristics with the same number of node expansions. Further, despite longer node evaluation times, RL guidance achieves better run-time performance than standard DIDP on three of four benchmark domains.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16371
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reinforcement Learning-based Heuristics to Guide Domain-Independent Dynamic Programming
Narita, Minori
Kuroiwa, Ryo
Beck, J. Christopher
Artificial Intelligence
Machine Learning
Domain-Independent Dynamic Programming (DIDP) is a state-space search paradigm based on dynamic programming for combinatorial optimization. In its current implementation, DIDP guides the search using user-defined dual bounds. Reinforcement learning (RL) is increasingly being applied to combinatorial optimization problems and shares several key structures with DP, being represented by the Bellman equation and state-based transition systems. We propose using reinforcement learning to obtain a heuristic function to guide the search in DIDP. We develop two RL-based guidance approaches: value-based guidance using Deep Q-Networks and policy-based guidance using Proximal Policy Optimization. Our experiments indicate that RL-based guidance significantly outperforms standard DIDP and problem-specific greedy heuristics with the same number of node expansions. Further, despite longer node evaluation times, RL guidance achieves better run-time performance than standard DIDP on three of four benchmark domains.
title Reinforcement Learning-based Heuristics to Guide Domain-Independent Dynamic Programming
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2503.16371