mlsanityData to 7 Oct 2026

Active Curriculum Refinement for Reinforcement Learning

arXiv 2608.26469 ↗First posted 26 Aug 2026cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 45 of its 54 references that are in the map. First posted on arXiv 26 Aug 2026.

Builds on

45 of 54 references.

References · 45

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  3. 2016OpenAI Gymcited by 1,684
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  5. 2018Experience Replay for Continual Learningcited by 1,074
  6. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  7. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  8. 2019Leveraging Procedural Generation to Benchmark Reinforcement Learningcited by 478
  9. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
  10. 2018Quantifying Generalization in Reinforcement Learningcited by 345
  11. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 260
  12. 2021Curriculum Learning: A Surveycited by 257
33 more
  1. 2017Automatic Goal Generation for Reinforcement Learning Agentscited by 252
  2. 2017Teacher-Student Curriculum Learningcited by 197
  3. 2020Prioritized Level Replaycited by 190
  4. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 185
  5. 2019Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutionscited by 182
  6. 2022Evolving Curricula with Regret-Based Environment Designcited by 166
  7. 2019Active Domain Randomizationcited by 161
  8. 2022Rapid Locomotion via Reinforcement Learningcited by 130
  9. 2019Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environmentscited by 113
  10. 2021Replay-Guided Adversarial Environment Designcited by 108
  11. 2018CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learningcited by 78
  12. 2022Automated Reinforcement Learning (AutoRL): A Survey and Open Problemscited by 69
  13. 2019Towards Practical Multi-Object Manipulation using Relational Reinforcement Learningcited by 54
  14. 2020Self-Paced Deep Reinforcement Learningcited by 49
  15. 2020Data-efficient Domain Randomization with Bayesian Optimizationcited by 43
  16. 2024No Regrets: Investigating and Improving Regret Approximations for Curriculum Discoverycited by 29
  17. 2021A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learningcited by 21
  18. 2022CLUTR: Curriculum Learning via Unsupervised Task Representation Learningcited by 19
  19. 2023Stabilizing Unsupervised Environment Design with a Learned Adversarycited by 17
  20. 2022Grounding Aleatoric Uncertainty for Unsupervised Environment Designcited by 16
  21. 2024Refining Minimax Regret for Unsupervised Environment Designcited by 16
  22. 2024Eurekaverse: Environment Curriculum Generation via Large Language Modelscited by 14
  23. 2020Guided Curriculum Learning for Walking Over Complex Terraincited by 10
  24. 2023Generalization through Diversity: Improving Unsupervised Environment Designcited by 9
  25. 2024Adversarial Environment Design via Regret-Guided Diffusion Modelscited by 9
  26. 2025An Optimisation Framework for Unsupervised Environment Designcited by 9
  27. 2024Curriculum-Based Reinforcement Learning for Quadrupedal Jumping: A Reference-free Designcited by 6
  28. 2024Proximal Curriculum with Task Correlations for Deep Reinforcement Learningcited by 6
  29. 2025Causally Aligned Curriculum Learningcited by 6
  30. 2021Discovering Generalizable Skills via Automated Generation of Diverse Taskscited by 5
  31. 2024Enabling Adaptive Agent Training in Open-Ended Simulators by Targeting Diversitycited by 3
  32. 2025GACL: Grounded Adaptive Curriculum Learning with Active Task and Performance Monitoringcited by 3
  33. 2025Automating Curriculum Learning for Reinforcement Learning using a Skill-Based Bayesian Networkcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Shared Actors Need Not Share Critics: Effects of Value Mismatch in Parallel Reinforcement Learningcited by 0