Active Curriculum Refinement for Reinforcement Learning

August 26, 2026 ยท Grace Period ยท ๐Ÿ› Proceedings of the International Conference on Machine Learning 2026

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Zhenya Liu, Yuxin Chen arXiv ID 2608.26469 Category cs.LG: Machine Learning Citations 0 Venue Proceedings of the International Conference on Machine Learning 2026
Abstract
In many reinforcement learning (RL) domains, environments are connected by prerequisite relations, such as difficulty-increasing edits or parameter increments, which induce a directed acyclic curriculum graph (DAG). Although this structure is often exploited only implicitly, explicitly modeling it can improve training. We introduce PATH, a curriculum-learning framework that performs active learning over the curriculum graph. PATH first expands coverage by sampling diverse curriculum paths and then reallocates training toward regions that remain unmastered. Experiments across diverse environments show that PATH explicitly leverages the graph structure to achieve strong robustness and generalization.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning