Summary of Learning to Ground Existentially Quantified Goals, by Martin Funkquist et al.
Learning to Ground Existentially Quantified Goals
by Martin Funkquist, Simon Ståhlberg, Hector Geffner
First submitted to arxiv on: 30 Sep 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed architecture addresses the goal grounding problem with a novel supervised learning approach, utilizing a Graph Neural Network (GNN) to predict the cost of partially quantified goals. The GNN is trained on small domain instances to generalize to larger instances involving more objects and different quantified goals. The approach is evaluated experimentally over several planning domains, testing generalization along dimensions such as goal variables and object bindings. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary AI agents need to achieve goals without assuming unique names for objects. Instead, descriptions are used, but this raises problems in both classical and generalized planning. To address the goal grounding problem, a novel supervised learning approach is proposed using GNNs. The architecture is trained on small instances to predict cost of partially quantified goals and generalizes to larger instances with more objects and different goals. |
Keywords
» Artificial intelligence » Generalization » Gnn » Graph neural network » Grounding » Supervised
