# Continual Reinforcement Learning with Multi-Timescale Replay

arXiv: https://arxiv.org/abs/2004.07530 · HTML: https://mlsanity.com/paper/2004.07530/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Powerpropagation: A sparsity inducing weight reparameterisation](https://mlsanity.com/paper/2110.00296/) (2021)
- [Sequoia: A Software Framework to Unify Continual Learning Research](https://mlsanity.com/paper/2108.01005/) (2021)
- [Prediction and Control in Continual Reinforcement Learning](https://mlsanity.com/paper/2312.11669/) (2023)
- [Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges](https://mlsanity.com/paper/2205.14495/) (2022)
- [Uncertainty Prioritized Experience Replay](https://mlsanity.com/paper/2506.09270/) (2025)
- [LoopSR: Looping Sim-and-Real for Lifelong Policy Adaptation of Legged Robots](https://mlsanity.com/paper/2409.17992/) (2024)
- [Sequence Adaptation via Reinforcement Learning in Recommender Systems](https://mlsanity.com/paper/2108.01442/) (2021)
- [Using Curiosity for an Even Representation of Tasks in Continual Offline Reinforcement Learning](https://mlsanity.com/paper/2312.03177/) (2023)
- [Data-Incremental Continual Offline Reinforcement Learning](https://mlsanity.com/paper/2404.12639/) (2024)

## Abstract (arXiv)

In this paper, we propose a multi-timescale replay (MTR) buffer for improving continual learning in RL agents faced with environments that are changing continuously over time at timescales that are unknown to the agent. The basic MTR buffer comprises a cascade of sub-buffers that accumulate experiences at different timescales, enabling the agent to improve the trade-off between adaptation to new data and retention of old knowledge. We also combine the MTR framework with invariant risk minimization, with the idea of encouraging the agent to learn a policy that is robust across the various environments it encounters over time. The MTR methods are evaluated in three different continual learning settings on two continuous control tasks and, in many cases, show improvement over the baselines.