Abstract Neuro-Symbolic Artificial Intelligence–the combination of symbolic methods with methods that are based on artificial neural networks–has a long-standing history. In this …
Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains …
It has been recently shown that general policies for many classical planning domains can be expressed and learned in terms of a pool of features defined from the domain predicates …
We consider the problem of learning generalized policies for classical planning domains using graph neural networks from small instances represented in lifted STRIPS. The …
While reinforcement learning methods have delivered remarkable results in a number of settings, generalization, ie, the ability to produce policies that generalize in a reliable and …
W Wang, Y Yang, F Wu - arXiv preprint arXiv:2210.15889, 2022 - arxiv.org
Neural-symbolic computing (NeSy), which pursues the integration of the symbolic and statistical paradigms of cognition, has been an active research area of Artificial Intelligence …
G Frances, B Bonet, H Geffner - … of the AAAI Conference on Artificial …, 2021 - ojs.aaai.org
Generalized planning is concerned with the computation of general policies that solve multiple instances of a planning domain all at once. It has been recently shown that these …
Reinforcement Learning (RL), bolstered by the expressive capabilities of Deep Neural Networks (DNNs) for function approximation, has demonstrated considerable success in …
DZ Chen, S Thiébaux, F Trevizan - … of the AAAI Conference on Artificial …, 2024 - ojs.aaai.org
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 …