A review of symbolic, subsymbolic and hybrid methods for sequential decision making

C Núñez-Molina, P Mesejo… - ACM Computing …, 2024 - dl.acm.org
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 …

Learning domain-independent planning heuristics with hypergraph networks

W Shen, F Trevizan, S Thiébaux - Proceedings of the International …, 2020 - aaai.org
We present the first approach capable of learning domain-independent planning heuristics
entirely from scratch. The heuristics we learn map the hypergraph representation of the …

Learning generalized policies without supervision using gnns

S Ståhlberg, B Bonet, H Geffner - ar** flexible AI systems is the split between data-based
learners and model-based solvers. Solvers such as classical planners are very flexible and …

Learning general planning policies from small examples without supervision

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 …

Generalized planning with deep reinforcement learning

O Rivlin, T Hazan, E Karpas - arxiv preprint arxiv:2005.02305, 2020 - arxiv.org
A hallmark of intelligence is the ability to deduce general principles from examples, which
are correct beyond the range of those observed. Generalized Planning deals with finding …

Learning generalized relational heuristic networks for model-agnostic planning

R Karia, S Srivastava - Proceedings of the AAAI Conference on Artificial …, 2021 - ojs.aaai.org
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 …