# Learn the Time to Learn: Replay Scheduling in Continual Learning

arXiv: https://arxiv.org/abs/2209.08660 · HTML: https://mlsanity.com/paper/2209.08660/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 74 of its 112 references that are in the map.
- First posted on arXiv 18 Sep 2022.

## Builds on (most cited first, 30 of 74)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Efficient Lifelong Learning with A-GEM](https://mlsanity.com/paper/1812.00420/) (2018)
- [Dark Experience for General Continual Learning: a Strong, Simple Baseline](https://mlsanity.com/paper/2004.07211/) (2020)
- [PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning](https://mlsanity.com/paper/1711.05769/) (2017)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence](https://mlsanity.com/paper/1801.10112/) (2018)
- [An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks](https://mlsanity.com/paper/1312.6211/) (2013)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Overcoming catastrophic forgetting with hard attention to the task](https://mlsanity.com/paper/1801.01423/) (2018)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Gradient based sample selection for online continual learning](https://mlsanity.com/paper/1903.08671/) (2019)
- [Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference](https://mlsanity.com/paper/1810.11910/) (2018)
- [Progress & Compress: A scalable framework for continual learning](https://mlsanity.com/paper/1805.06370/) (2018)
- [Online Continual Learning with Maximally Interfered Retrieval](https://mlsanity.com/paper/1908.04742/) (2019)

## Built on by (most cited first, 11 of 11)

- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning](https://mlsanity.com/paper/2603.09892/) (2026)
- [Adiabatic replay for continual learning](https://mlsanity.com/paper/2303.13157/) (2023)
- [TMS: Trajectory-Mixed Supervision for Reward-Free, On-Policy SFT](https://mlsanity.com/paper/2602.03073/) (2026)
- [RAIE: Region-Aware Incremental Preference Editing with LoRA for LLM-based Recommendation](https://mlsanity.com/paper/2603.00638/) (2026)
- [Measuring the Value of World-Model Updates: A Counterfactual Utility Protocol for Continual Adaptation](https://mlsanity.com/paper/2609.10954/) (2026)
- [Brain-Inspired Continual Learning-Robust Feature Distillation and Re-Consolidation for Class Incremental Learning](https://mlsanity.com/paper/2404.14588/) (2024)
- [Adaptive Variational Continual Learning via Task-Heuristic Modelling](https://mlsanity.com/paper/2408.16517/) (2024)
- [Low-Rank Filtering and Smoothing for Sequential Deep Learning](https://mlsanity.com/paper/2410.06800/) (2024)
- [Beyond Class Marginals: Bounding Rehearsal Gaps without Freezing Class Co-occurrence](https://mlsanity.com/paper/2609.25735/) (2026)
- [Replay in the Silent Degrees of Freedom: Continual Learning Without an Offline Phase](https://mlsanity.com/paper/2609.31630/) (2026)

## Abstract (arXiv)

Replay methods are known to be successful at mitigating catastrophic forgetting in continual learning scenarios despite having limited access to historical data. However, storing historical data is cheap in many real-world settings, yet replaying all historical data is often prohibited due to processing time constraints. In such settings, we propose that continual learning systems should learn the time to learn and schedule which tasks to replay at different time steps. We first demonstrate the benefits of our proposal by using Monte Carlo tree search to find a proper replay schedule, and show that the found replay schedules can outperform fixed scheduling policies when combined with various replay methods in different continual learning settings. Additionally, we propose a framework for learning replay scheduling policies with reinforcement learning. We show that the learned policies can generalize better in new continual learning scenarios compared to equally replaying all seen tasks, without added computational cost. Our study reveals the importance of learning the time to learn in continual learning, which brings current research closer to real-world needs.