Summary of Learning For Long-horizon Planning Via Neuro-symbolic Abductive Imitation, by Jie-jing Shao et al.
Learning for Long-Horizon Planning via Neuro-Symbolic Abductive Imitation
by Jie-Jing Shao, Hao-Ran Hao, Xiao-Wen Yang, Yu-Feng Li
First submitted to arxiv on: 27 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 novel framework ABductive Imitation Learning (ABIL) combines the strengths of data-driven learning and symbolic-based reasoning to enable long-horizon planning. It employs abductive reasoning to understand demonstrations in symbolic space, designs principles for sequential consistency to resolve conflicts between perception and reasoning, and generates predicate candidates to facilitate the perception from raw observations to symbolic space without laborious predicate annotations. The policy ensemble built with different logical objectives and managed through symbolic reasoning demonstrates improved data efficiency and generalization across various long-horizon tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary ABIL helps plan for a long time by combining two good ideas: learning from examples (like humans do) and using rules (like computers do). It takes in things that people or machines have done before and tries to figure out why they did it. Then, it uses this understanding to make new plans, even if those plans are really long-term. This helps with tasks like making a robot plan how to get from point A to point B while avoiding obstacles. |
Keywords
* Artificial intelligence * Generalization
