Model Releases
Active Curriculum Refinement for Reinforcement Learning
arXiv:2608.26469v1 Announce Type: new Abstract: In many reinforcement learning (RL) domains, environments are connected by prerequisite relations, such as difficulty-increasing edits or parameter incr
arXiv:2608.26469v1 Announce Type: new 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.
Related
- Environment Parameter Gradient Theorem for Policy-Environment Co-Design in Reinforcement Learning
- Two-Timescale Hierarchical Reinforcement Learning for Resilient Operations
- Hierarchical Reinforcement Learning with Optimal Level Synchronization Based on Flow-Based Deep Generative Model
- Hadamard Representation: Scaffolding Performance Across Model-free RL
Source: arXiv cs.LG | 2026-08-28