# Effect of Optimizer, Initializer, and Architecture of Hypernetworks on Continual Learning from Demonstration

arXiv: https://arxiv.org/abs/2401.00524 · HTML: https://mlsanity.com/paper/2401.00524/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Robot learning from demonstration, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 31 Dec 2023.

## Placed in

- Offline RL and imitation learning from data / [Robot learning from demonstration](https://mlsanity.com/offlinerl/robot-learning-from-demonstration/)

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [Learning Stable Deep Dynamics Models](https://mlsanity.com/paper/2001.06116/) (2020)
- [Continual Model-Based Reinforcement Learning with Hypernetworks](https://mlsanity.com/paper/2009.11997/) (2020)
- [ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows](https://mlsanity.com/paper/2010.13129/) (2020)
- [Principled Weight Initialization for Hypernetworks](https://mlsanity.com/paper/2312.08399/) (2023)
- [Continual Learning from Demonstration of Robotics Skills](https://mlsanity.com/paper/2202.06843/) (2022)
- [Scalable and Efficient Continual Learning from Demonstration via a Hypernetwork-generated Stable Dynamics Model](https://mlsanity.com/paper/2311.03600/) (2023)

## Built on by (most cited first, 2 of 2)

- [HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworks](https://mlsanity.com/paper/2510.04898/) (2025)
- [On Understanding of the Dynamics of Model Capacity in Continual Learning](https://mlsanity.com/paper/2508.08052/) (2025)

## Abstract (arXiv)

In continual learning from demonstration (CLfD), a robot learns a sequence of real-world motion skills continually from human demonstrations. Recently, hypernetworks have been successful in solving this problem. In this paper, we perform an exploratory study of the effects of different optimizers, initializers, and network architectures on the continual learning performance of hypernetworks for CLfD. Our results show that adaptive learning rate optimizers work well, but initializers specially designed for hypernetworks offer no advantages for CLfD. We also show that hypernetworks that are capable of stable trajectory predictions are robust to different network architectures. Our open-source code is available at https://github.com/sebastianbergner/ExploringCLFD.