Active Curriculum Refinement for Reinforcement Learning

2026-08-26

AI Summary

本文提出PATH框架，通过主动学习课程图来解决强化学习中环境间的先决关系问题，以提高训练效果和泛化能力。

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.

Problem

• reinforcement learning
• curriculum graph
• prerequisite relations

Innovation

• Curriculum Learning
• Reinforcement Learning
• Active Learning
• DAG