# Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL

arXiv: https://arxiv.org/abs/1812.07671 · HTML: https://mlsanity.com/paper/1812.07671/

## Key facts

- Cited by 81 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2018.

## Built on by (most cited first, 30 of 81)

- [Online Continual Learning in Image Classification: An Empirical Survey](https://mlsanity.com/paper/2101.10423/) (2021)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [A Survey on Model-based Reinforcement Learning](https://mlsanity.com/paper/2206.09328/) (2022)
- [GNNDelete: A General Strategy for Unlearning in Graph Neural Networks](https://mlsanity.com/paper/2302.13406/) (2023)
- [Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment](https://mlsanity.com/paper/2104.05632/) (2021)
- [Offline Meta-Reinforcement Learning for Industrial Insertion](https://mlsanity.com/paper/2110.04276/) (2021)
- [Skill-based Meta-Reinforcement Learning](https://mlsanity.com/paper/2204.11828/) (2022)
- [MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild](https://mlsanity.com/paper/2603.17187/) (2026)
- [Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability](https://mlsanity.com/paper/2209.08025/) (2022)
- [Context-Aware Safe Reinforcement Learning for Non-Stationary Environments](https://mlsanity.com/paper/2101.00531/) (2021)
- [A Closer Look at Learned Optimization: Stability, Robustness, and Inductive Biases](https://mlsanity.com/paper/2209.11208/) (2022)
- [Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along Time](https://mlsanity.com/paper/2108.06721/) (2021)
- [Building a Subspace of Policies for Scalable Continual Learning](https://mlsanity.com/paper/2211.10445/) (2022)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [Block Contextual MDPs for Continual Learning](https://mlsanity.com/paper/2110.06972/) (2021)
- [Formalizing the Generalization-Forgetting Trade-off in Continual Learning](https://mlsanity.com/paper/2109.14035/) (2021)
- [DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting](https://mlsanity.com/paper/2306.09862/) (2023)
- [Fairness-Aware Online Meta-learning](https://mlsanity.com/paper/2108.09435/) (2021)
- [HyperDynamics: Meta-Learning Object and Agent Dynamics with Hypernetworks](https://mlsanity.com/paper/2103.09439/) (2021)
- [Minimum-Delay Adaptation in Non-Stationary Reinforcement Learning via Online High-Confidence Change-Point Detection](https://mlsanity.com/paper/2105.09452/) (2021)
- [A Survey of Continual Reinforcement Learning](https://mlsanity.com/paper/2506.21872/) (2025)
- [Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy](https://mlsanity.com/paper/2207.12141/) (2022)
- [The Effectiveness of World Models for Continual Reinforcement Learning](https://mlsanity.com/paper/2211.15944/) (2022)
- [On the link between conscious function and general intelligence in humans and machines](https://mlsanity.com/paper/2204.05133/) (2022)
- [Curious Replay for Model-based Adaptation](https://mlsanity.com/paper/2306.15934/) (2023)
- [CoMPS: Continual Meta Policy Search](https://mlsanity.com/paper/2112.04467/) (2021)
- [A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning](https://mlsanity.com/paper/2206.04551/) (2022)
- [An Adaptive Deep RL Method for Non-Stationary Environments with Piecewise Stable Context](https://mlsanity.com/paper/2212.12735/) (2022)
- [MLDemon: Deployment Monitoring for Machine Learning Systems](https://mlsanity.com/paper/2104.13621/) (2021)
- [Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization](https://mlsanity.com/paper/2209.00347/) (2022)

## Abstract (arXiv)

Humans and animals can learn complex predictive models that allow them to accurately and reliably reason about real-world phenomena, and they can adapt such models extremely quickly in the face of unexpected changes. Deep neural network models allow us to represent very complex functions, but lack this capacity for rapid online adaptation. The goal in this paper is to develop a method for continual online learning from an incoming stream of data, using deep neural network models. We formulate an online learning procedure that uses stochastic gradient descent to update model parameters, and an expectation maximization algorithm with a Chinese restaurant process prior to develop and maintain a mixture of models to handle non-stationary task distributions. This allows for all models to be adapted as necessary, with new models instantiated for task changes and old models recalled when previously seen tasks are encountered again. Furthermore, we observe that meta-learning can be used to meta-train a model such that this direct online adaptation with SGD is effective, which is otherwise not the case for large function approximators. In this work, we apply our meta-learning for online learning (MOLe) approach to model-based reinforcement learning, where adapting the predictive model is critical for control; we demonstrate that MOLe outperforms alternative prior methods, and enables effective continuous adaptation in non-stationary task distributions such as varying terrains, motor failures, and unexpected disturbances.