mlsanityData to 7 Oct 2026

Teacher-Student Curriculum Learning

arXiv 1707.00183 ↗First posted 1 Jul 2017cs.LG cs.AIcited by 197

Not on the map. Why?

Abstract (arXiv)

We propose Teacher-Student Curriculum Learning (TSCL), a framework for automatic curriculum learning, where the Student tries to learn a complex task and the Teacher automatically chooses subtasks from a given set for the Student to train on. We describe a family of Teacher algorithms that rely on the intuition that the Student should practice more those tasks on which it makes the fastest progress, i.e. where the slope of the learning curve is highest. In addition, the Teacher algorithms address the problem of forgetting by also choosing tasks where the Student's performance is getting worse. We demonstrate that TSCL matches or surpasses the results of carefully hand-crafted curricula in two tasks: addition of decimal numbers with LSTM and navigation in Minecraft. Using our automatically generated curriculum enabled to solve a Minecraft maze that could not be solved at all when training directly on solving the maze, and the learning was an order of magnitude faster than uniform sampling of subtasks.

Key facts. Cited by 197 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 33; 2022: 37; 2023: 25; 2024: 30; 2025: 27; 2026: 44.

197 papers.

Sort:

By area:

  1. 2022Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videoscited by 338
  2. 2021Curriculum Learning: A Surveycited by 257
  3. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 177
  4. 2022Evolving Curricula with Regret-Based Environment Designcited by 166
  5. 2023Human-Timescale Adaptation in an Open-Ended Task Spacecited by 136
  6. 2022Rapid Locomotion via Reinforcement Learningcited by 130
  7. 2021Replay-Guided Adversarial Environment Designcited by 108
  8. 2025Self-Evolving Curriculum for LLM Reasoningcited by 107
  9. 2025Efficient Reinforcement Finetuning via Adaptive Curriculum Learningcited by 88
  10. 2021Asymmetric self-play for automatic goal discovery in robotic manipulationcited by 71
  11. 2022Automated Reinforcement Learning (AutoRL): A Survey and Open Problemscited by 69
  12. 2022Music Source Separation with Band-split RNNcited by 69
38 more
  1. 2023OMNI: Open-endedness via Models of human Notions of Interestingnesscited by 66
  2. 2021Uncertainty-Aware Unsupervised Domain Adaptation in Object Detectioncited by 59
  3. 2023How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligencecited by 55
  4. 2023Towards A Unified Agent with Foundation Modelscited by 46
  5. 2025DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-trainingcited by 45
  6. 2025MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agentscited by 43
  7. 2022EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbonescited by 42
  8. 2022Contextualize Me -- The Case for Context in Reinforcement Learningcited by 41
  9. 2022Curriculum Learning for Dense Retrieval Distillationcited by 38
  10. 2021Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraftcited by 34
  11. 2025Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interactioncited by 34
  12. 2023MCU: An Evaluation Framework for Open-Ended Game Agentscited by 33
  13. 2021Autonomous Reinforcement Learning via Subgoal Curriculacited by 32
  14. 2022Environment Generation for Zero-Shot Compositional Reinforcement Learningcited by 32
  15. 2023MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learningcited by 30
  16. 2021Bridging Pre-trained Models and Downstream Tasks for Source Code Understandingcited by 27
  17. 2023Teacher-Student Architecture for Knowledge Distillation: A Surveycited by 26
  18. 2024Modality-Fair Preference Optimization for Trustworthy MLLM Alignmentcited by 26
  19. 2021Self-Paced Context Evaluation for Contextual Reinforcement Learningcited by 25
  20. 2021Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problemscited by 25
  21. 2022Teacher-Student Architecture for Knowledge Learning: A Surveycited by 23
  22. 2021Medical Image Segmentation with Limited Supervision: A Review of Deep Network Modelscited by 21
  23. 2021CARL: A Benchmark for Contextual and Adaptive Reinforcement Learningcited by 21
  24. 2022Mind the gap: Challenges of deep learning approaches to Theory of Mindcited by 21
  25. 2024Weak-to-Strong Generalization Through the Data-Centric Lenscited by 21
  26. 2024A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoalscited by 20
  27. 2025Learning to Reason at the Frontier of Learnabilitycited by 20
  28. 2021Solving Compositional Reinforcement Learning Problems via Task Reductioncited by 19
  29. 2023Proximal Curriculum for Reinforcement Learning Agentscited by 19
  30. 2023Domain Generalization via Balancing Training Difficulty and Model Capabilitycited by 19
  31. 2024CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Modelscited by 19
  32. 2021TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RLcited by 18
  33. 2021Curriculum Learning for Vision-and-Language Navigationcited by 18
  34. 2022GraB: Finding Provably Better Data Permutations than Random Reshufflingcited by 18
  35. 2022Grounding Aleatoric Uncertainty for Unsupervised Environment Designcited by 16
  36. 2024EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Trainingcited by 16
  37. 2024RealCustom++: Representing Images as Real Textual Word for Real-Time Customizationcited by 16
  38. 2022Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localizationcited by 14

50 most cited of 197 All 197 (JSON)