Active Curriculum Refinement for Reinforcement Learning
cs.LG
Submitted: 2026-08-26
Updated: 2026-08-26
Journal ref: Proceedings of the International Conference on Machine Learning 2026
Code: https://github.com/Liu-Zhenya/PATH
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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
Terminology
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.
Sources
- Curriculum-Based Reinforcement Learning for Quadrupedal Jumping: A Reference-free Design
- OpenAI Gym
- Training language models to follow instructions with human feedback
- Teacher-Student Curriculum Learning
- Guided Curriculum Learning for Walking Over Complex Terrain
- Proximal Policy Optimization Algorithms
- Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
- C-Procgen: Empowering Procgen with Controllable Contexts
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks