# Teacher-Student Curriculum Learning

arXiv: https://arxiv.org/abs/1707.00183 · HTML: https://mlsanity.com/paper/1707.00183/

## Key facts

- Cited by 210 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2017.

## Built on by (most cited first, 30 of 210)

- [Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos](https://mlsanity.com/paper/2206.11795/) (2022)
- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Open-Ended Learning Leads to Generally Capable Agents](https://mlsanity.com/paper/2107.12808/) (2021)
- [Evolving Curricula with Regret-Based Environment Design](https://mlsanity.com/paper/2203.01302/) (2022)
- [Rapid Locomotion via Reinforcement Learning](https://mlsanity.com/paper/2205.02824/) (2022)
- [Human-Timescale Adaptation in an Open-Ended Task Space](https://mlsanity.com/paper/2301.07608/) (2023)
- [Self-Evolving Curriculum for LLM Reasoning](https://mlsanity.com/paper/2505.14970/) (2025)
- [Replay-Guided Adversarial Environment Design](https://mlsanity.com/paper/2110.02439/) (2021)
- [Efficient Reinforcement Finetuning via Adaptive Curriculum Learning](https://mlsanity.com/paper/2504.05520/) (2025)
- [Asymmetric self-play for automatic goal discovery in robotic manipulation](https://mlsanity.com/paper/2101.04882/) (2021)
- [Automated Reinforcement Learning (AutoRL): A Survey and Open Problems](https://mlsanity.com/paper/2201.03916/) (2022)
- [Music Source Separation with Band-split RNN](https://mlsanity.com/paper/2209.15174/) (2022)
- [OMNI: Open-endedness via Models of human Notions of Interestingness](https://mlsanity.com/paper/2306.01711/) (2023)
- [Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection](https://mlsanity.com/paper/2103.00236/) (2021)
- [How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence](https://mlsanity.com/paper/2305.01263/) (2023)
- [Towards A Unified Agent with Foundation Models](https://mlsanity.com/paper/2307.09668/) (2023)
- [Contextualize Me -- The Case for Context in Reinforcement Learning](https://mlsanity.com/paper/2202.04500/) (2022)
- [DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training](https://mlsanity.com/paper/2504.09710/) (2025)
- [EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones](https://mlsanity.com/paper/2211.09703/) (2022)
- [MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents](https://mlsanity.com/paper/2509.18119/) (2025)
- [Curriculum Learning for Dense Retrieval Distillation](https://mlsanity.com/paper/2204.13679/) (2022)
- [Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft](https://mlsanity.com/paper/2106.14876/) (2021)
- [MCU: An Evaluation Framework for Open-Ended Game Agents](https://mlsanity.com/paper/2310.08367/) (2023)
- [Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction](https://mlsanity.com/paper/2506.07976/) (2025)
- [Autonomous Reinforcement Learning via Subgoal Curricula](https://mlsanity.com/paper/2107.12931/) (2021)
- [Environment Generation for Zero-Shot Compositional Reinforcement Learning](https://mlsanity.com/paper/2201.08896/) (2022)
- [MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2303.03376/) (2023)
- [Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding](https://mlsanity.com/paper/2112.02268/) (2021)
- [Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems](https://mlsanity.com/paper/2111.04613/) (2021)
- [Teacher-Student Architecture for Knowledge Distillation: A Survey](https://mlsanity.com/paper/2308.04268/) (2023)

## 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.