SYNAPSE: SYmbolic Neural-Aided Preference Synthesis Engine
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909456702373888 |
|---|---|
| author | Modak, Sadanand Patton, Noah Dillig, Isil Biswas, Joydeep |
| author_facet | Modak, Sadanand Patton, Noah Dillig, Isil Biswas, Joydeep |
| contents | This paper addresses the problem of preference learning, which aims to align robot behaviors through learning user specific preferences (e.g. "good pull-over location") from visual demonstrations. Despite its similarity to learning factual concepts (e.g. "red door"), preference learning is a fundamentally harder problem due to its subjective nature and the paucity of person-specific training data. We address this problem using a novel framework called SYNAPSE, which is a neuro-symbolic approach designed to efficiently learn preferential concepts from limited data. SYNAPSE represents preferences as neuro-symbolic programs, facilitating inspection of individual parts for alignment, in a domain-specific language (DSL) that operates over images and leverages a novel combination of visual parsing, large language models, and program synthesis to learn programs representing individual preferences. We perform extensive evaluations on various preferential concepts as well as user case studies demonstrating its ability to align well with dissimilar user preferences. Our method significantly outperforms baselines, especially when it comes to out of distribution generalization. We show the importance of the design choices in the framework through multiple ablation studies. Code, additional results, and supplementary material can be found on the website: https://amrl.cs.utexas.edu/synapse |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16689 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SYNAPSE: SYmbolic Neural-Aided Preference Synthesis Engine Modak, Sadanand Patton, Noah Dillig, Isil Biswas, Joydeep Robotics Computer Vision and Pattern Recognition Machine Learning Programming Languages This paper addresses the problem of preference learning, which aims to align robot behaviors through learning user specific preferences (e.g. "good pull-over location") from visual demonstrations. Despite its similarity to learning factual concepts (e.g. "red door"), preference learning is a fundamentally harder problem due to its subjective nature and the paucity of person-specific training data. We address this problem using a novel framework called SYNAPSE, which is a neuro-symbolic approach designed to efficiently learn preferential concepts from limited data. SYNAPSE represents preferences as neuro-symbolic programs, facilitating inspection of individual parts for alignment, in a domain-specific language (DSL) that operates over images and leverages a novel combination of visual parsing, large language models, and program synthesis to learn programs representing individual preferences. We perform extensive evaluations on various preferential concepts as well as user case studies demonstrating its ability to align well with dissimilar user preferences. Our method significantly outperforms baselines, especially when it comes to out of distribution generalization. We show the importance of the design choices in the framework through multiple ablation studies. Code, additional results, and supplementary material can be found on the website: https://amrl.cs.utexas.edu/synapse |
| title | SYNAPSE: SYmbolic Neural-Aided Preference Synthesis Engine |
| topic | Robotics Computer Vision and Pattern Recognition Machine Learning Programming Languages |
| url | https://arxiv.org/abs/2403.16689 |