Interleaved Multitask Learning with Energy Modulated Learning Progress
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913960107704320 |
|---|---|
| author | Say, Hanne Ada, Suzan Ece Ugur, Emre Asada, Minoru Oztop, Erhan |
| author_facet | Say, Hanne Ada, Suzan Ece Ugur, Emre Asada, Minoru Oztop, Erhan |
| contents | As humans learn new skills and apply their existing knowledge while maintaining previously learned information, "continual learning" in machine learning aims to incorporate new data while retaining and utilizing past knowledge. However, existing machine learning methods often does not mimic human learning where tasks are intermixed due to individual preferences and environmental conditions. Humans typically switch between tasks instead of completely mastering one task before proceeding to the next. To explore how human-like task switching can enhance learning efficiency, we propose a multi task learning architecture that alternates tasks based on task-agnostic measures such as "learning progress" and "neural computational energy expenditure". To evaluate the efficacy of our method, we run several systematic experiments by using a set of effect-prediction tasks executed by a simulated manipulator robot. The experiments show that our approach surpasses random interleaved and sequential task learning in terms of average learning accuracy. Moreover, by including energy expenditure in the task switching logic, our approach can still perform favorably while reducing neural energy expenditure. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_00707 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interleaved Multitask Learning with Energy Modulated Learning Progress Say, Hanne Ada, Suzan Ece Ugur, Emre Asada, Minoru Oztop, Erhan Robotics Artificial Intelligence Machine Learning As humans learn new skills and apply their existing knowledge while maintaining previously learned information, "continual learning" in machine learning aims to incorporate new data while retaining and utilizing past knowledge. However, existing machine learning methods often does not mimic human learning where tasks are intermixed due to individual preferences and environmental conditions. Humans typically switch between tasks instead of completely mastering one task before proceeding to the next. To explore how human-like task switching can enhance learning efficiency, we propose a multi task learning architecture that alternates tasks based on task-agnostic measures such as "learning progress" and "neural computational energy expenditure". To evaluate the efficacy of our method, we run several systematic experiments by using a set of effect-prediction tasks executed by a simulated manipulator robot. The experiments show that our approach surpasses random interleaved and sequential task learning in terms of average learning accuracy. Moreover, by including energy expenditure in the task switching logic, our approach can still perform favorably while reducing neural energy expenditure. |
| title | Interleaved Multitask Learning with Energy Modulated Learning Progress |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2504.00707 |