Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.21166 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917940447674368 |
|---|---|
| author | Satici, Muhammed Yusuf Wang, Jianxun Roberts, David L. |
| author_facet | Satici, Muhammed Yusuf Wang, Jianxun Roberts, David L. |
| contents | Curriculum learning is a training method in which an agent is first trained on a curriculum of relatively simple tasks related to a target task in an effort to shorten the time required to train on the target task. Autonomous curriculum design involves the design of such curriculum with no reliance on human knowledge and/or expertise. Finding an efficient and effective way of autonomously designing curricula remains an open problem. We propose a novel approach for automatically designing curricula by leveraging the learner's uncertainty to select curricula tasks. Our approach measures the uncertainty in the learner's policy using relative entropy, and guides the agent to states of high uncertainty to facilitate learning. Our algorithm supports the generation of autonomous curricula in a self-assessed manner by leveraging the learner's past and current policies but it also allows the use of teacher guided design in an instructive setting. We provide theoretical guarantees for the convergence of our algorithm using two time-scale optimization processes. Results show that our algorithm outperforms randomly generated curriculum, and learning directly on the target task as well as the curriculum-learning criteria existing in literature. We also present two additional heuristic distance measures that could be combined with our relative-entropy approach for further performance improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_21166 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Autonomous Curriculum Design via Relative Entropy Based Task Modifications Satici, Muhammed Yusuf Wang, Jianxun Roberts, David L. Machine Learning Curriculum learning is a training method in which an agent is first trained on a curriculum of relatively simple tasks related to a target task in an effort to shorten the time required to train on the target task. Autonomous curriculum design involves the design of such curriculum with no reliance on human knowledge and/or expertise. Finding an efficient and effective way of autonomously designing curricula remains an open problem. We propose a novel approach for automatically designing curricula by leveraging the learner's uncertainty to select curricula tasks. Our approach measures the uncertainty in the learner's policy using relative entropy, and guides the agent to states of high uncertainty to facilitate learning. Our algorithm supports the generation of autonomous curricula in a self-assessed manner by leveraging the learner's past and current policies but it also allows the use of teacher guided design in an instructive setting. We provide theoretical guarantees for the convergence of our algorithm using two time-scale optimization processes. Results show that our algorithm outperforms randomly generated curriculum, and learning directly on the target task as well as the curriculum-learning criteria existing in literature. We also present two additional heuristic distance measures that could be combined with our relative-entropy approach for further performance improvements. |
| title | Autonomous Curriculum Design via Relative Entropy Based Task Modifications |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2502.21166 |