Summary of On Learning Action Costs From Input Plans, by Marianela Morales et al.
On Learning Action Costs from Input Plans
by Marianela Morales, Alberto Pozanco, Giuseppe Canonaco, Sriram Gopalakrishnan, Daniel Borrajo, Manuela Veloso
First submitted to arxiv on: 20 Aug 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 paper introduces a new problem in learning action models, focusing on learning the costs of actions rather than their dynamics. This allows for ranking different plans based on their optimality under a planning model. The authors present an algorithm called LACFIP^k that learns these action costs from unlabeled input plans and demonstrate its effectiveness through theoretical and empirical results. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper is about how to learn the cost of actions, which helps us rank different plans in a planning task. Right now, most work on this topic focuses on learning how actions work together, but not how much it costs to do each action. The authors come up with a new algorithm called LACFIP^k that can learn these costs from examples and show that it works well. |
