mlsanityData to 7 Oct 2026

Rethinking Teacher-Student Curriculum Learning through the Cooperative Mechanics of Experience

arXiv 2404.03084 ↗First posted 3 Apr 2024cs.LG cs.AI cs.GTcited by 1

Not on the map. Why?

Abstract (arXiv)

Teacher-Student Curriculum Learning (TSCL) is a curriculum learning framework that draws inspiration from human cultural transmission and learning. It involves a teacher algorithm shaping the learning process of a learner algorithm by exposing it to controlled experiences. Despite its success, understanding the conditions under which TSCL is effective remains challenging. In this paper, we propose a data-centric perspective to analyze the underlying mechanics of the teacher-student interactions in TSCL. We leverage cooperative game theory to describe how the composition of the set of experiences presented by the teacher to the learner, as well as their order, influences the performance of the curriculum that is found by TSCL approaches. To do so, we demonstrate that for every TSCL problem, an equivalent cooperative game exists, and several key components of the TSCL framework can be reinterpreted using game-theoretic principles. Through experiments covering supervised learning, reinforcement learning, and classical games, we estimate the cooperative values of experiences and use value-proportional curriculum mechanisms to construct curricula, even in cases where TSCL struggles. The framework and experimental setup we present in this work represents a novel foundation for a deeper exploration of TSCL, shedding light on its underlying mechanisms and providing insights into its broader applicability in machine learning.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 49 of its 109 references that are in the map. First posted on arXiv 3 Apr 2024.

Builds on

49 of 109 references.

References · 49

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  6. 2017Hindsight Experience Replaycited by 1,096
  7. 2015Prioritized Experience Replaycited by 1,070
  8. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 617
  9. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 367
  10. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 350
  11. 2017CORe50: a New Dataset and Benchmark for Continuous Object Recognitioncited by 287
  12. 2017A Unified Game-Theoretic Approach to Multiagent Reinforcement Learningcited by 265
37 more
  1. 2021Curriculum Learning: A Surveycited by 257
  2. 2017Automatic Goal Generation for Reinforcement Learning Agentscited by 252
  3. 2017Automated Curriculum Learning for Neural Networkscited by 251
  4. 2019Pareto Multi-Task Learningcited by 224
  5. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 218
  6. 2017Teacher-Student Curriculum Learningcited by 197
  7. 2017Reverse Curriculum Generation for Reinforcement Learningcited by 185
  8. 2020Revisiting Fundamentals of Experience Replaycited by 171
  9. 2018Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networkscited by 113
  10. 2019Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environmentscited by 113
  11. 2020When Do Curricula Work?cited by 105
  12. 2021Sampling Permutations for Shapley Value Estimationcited by 101
  13. 2018The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimizationcited by 98
  14. 2019Open-ended Learning in Symmetric Zero-sum Gamescited by 96
  15. 2022The CLEAR Benchmark: Continual LEArning on Real-World Imagerycited by 92
  16. 2020Learning with AMIGo: Adversarially Motivated Intrinsic Goalscited by 86
  17. 2020A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learningcited by 86
  18. 2021Continual Learning in the Teacher-Student Setup: Impact of Task Similaritycited by 86
  19. 2020Safe Reinforcement Learning via Curriculum Inductioncited by 73
  20. 2022CLiMB: A Continual Learning Benchmark for Vision-and-Language Taskscited by 68
  21. 2020EigenGame: PCA as a Nash Equilibriumcited by 39
  22. 2021Data Shapley Valuation for Efficient Batch Active Learningcited by 27
  23. 2022Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Trainingcited by 26
  24. 2021Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversitycited by 22
  25. 2020GANs May Have No Nash Equilibriacited by 20
  26. 2019What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?cited by 19
  27. 2022Linking Emergent and Natural Languages via Corpus Transfercited by 19
  28. 2021TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RLcited by 18
  29. 2020Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactionscited by 14
  30. 2022NeuPL: Neural Population Learningcited by 14
  31. 2022It Takes Four to Tango: Multiagent Selfplay for Automatic Curriculum Generationcited by 14
  32. 2020Negotiating Team Formation Using Deep Reinforcement Learningcited by 13
  33. 2023Auxiliary Learning as an Asymmetric Bargaining Gamecited by 12
  34. 2020Adam with Bandit Sampling for Deep Learningcited by 10
  35. 2021A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instancescited by 9
  36. 2021Game of GANs: Game-Theoretical Models for Generative Adversarial Networkscited by 6
  37. 2021Disentangling Transfer and Interference in Multi-Domain Learningcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Heterogeneous Adversarial Play in Interactive Environmentscited by 3