@misc{10481/96375,
year = {2024},
month = {6},
url = {https://hdl.handle.net/10481/96375},
abstract = {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., novel learn to plan techniques) for solving Sequential Decision Processes (SDPs), focusing on their knowledge representation: symbolic, subsymbolic, or a combination. Additionally, it also covers methods for learning the SDP structure. Finally, we compare the advantages and drawbacks of the existing methods and conclude that neurosymbolic AI poses a promising approach for SDM, since it combines AP and RL with a hybrid knowledge representation.},
organization = {Grant PID2022-142976OB-I00, funded by MCIN/AEI/ 10.13039/501100011033},
organization = {“ERDF A way of making Europe”},
organization = {Andalusian Regional predoctoral grant no. 21-111-PREDOC-0039
and by “ESF Investing in your future”},
organization = {Project CONFIA
(grant PID2021-122916NB-I00), funded by MICIU/AEI/10.13039/5011000 11033/ and by ERDF/EU},
publisher = {Association for Computing Machinery},
title = {A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making},
doi = {10.1145/3663366},
author = {Núñez Molina, Carlos and Mesejo Santiago, Pablo and Fernández Olivares, Juan},
}