mlsanityData to 14 Oct 2026

Automating Curriculum Learning for Reinforcement Learning using a Skill-Based Bayesian Network

arXiv 2502.15662 ↗First posted 21 Feb 2025cs.AI cs.LGcited by 1

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

A major challenge for reinforcement learning is automatically generating curricula to reduce training time or improve performance in some target task. We introduce SEBNs (Skill-Environment Bayesian Networks) which model a probabilistic relationship between a set of skills, a set of goals that relate to the reward structure, and a set of environment features to predict policy performance on (possibly unseen) tasks. We develop an algorithm that uses the inferred estimates of agent success from SEBN to weigh the possible next tasks by expected improvement. We evaluate the benefit of the resulting curriculum on three environments: a discrete gridworld, continuous control, and simulated robotics. The results show that curricula constructed using SEBN frequently outperform other baselines.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 13 of its 41 references that are in the map. First posted on arXiv 21 Feb 2025.

Builds on

13 of 41 references.

References · 13

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
  3. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  4. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 275
  5. 2016Modular Multitask Reinforcement Learning with Policy Sketchescited by 203
  6. 2022Evolving Curricula with Regret-Based Environment Designcited by 173
  7. 2021Replay-Guided Adversarial Environment Designcited by 111
  8. 2018Hierarchical Imitation and Reinforcement Learningcited by 88
  9. 2019Leveraging Human Guidance for Deep Reinforcement Learning Taskscited by 42
  10. 2024Practice Makes Perfect: Planning to Learn Skill Parameter Policiescited by 23
  11. 2017Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfercited by 19
  12. 2019Learn and Link: Learning Critical Regions for Efficient Planningcited by 7
1 more
  1. 2020FORK: A Forward-Looking Actor For Model-Free Reinforcement Learningcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Active Curriculum Refinement for Reinforcement Learningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Probabilistic Curriculum Learning for Goal-Based Reinforcement Learning
  2. 2025Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning
  3. 2026Anticipating the Consequences of Curriculum Decisions with Large Language Models
  4. 2024Syllabus: Portable Curricula for Reinforcement Learning Agents
  5. 2023CQM: Curriculum Reinforcement Learning with a Quantized World Model
  6. 2022Bayesian Nonparametrics for Offline Skill Discovery
  7. 2024Grounded Curriculum Learning
  8. 2026SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization