mlsanityData to 7 Oct 2026

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

arXiv 2401.00524 ↗First posted 31 Dec 2023cs.RO cs.LGcited by 2

On the map: Offline RL and imitation learning from data → Robot learning from demonstration

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.

Key facts. Cited by 2 papers in the map (data through 7 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.

Builds on

11 of 17 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023Scalable and Efficient Continual Learning from Demonstration via a Hypernetwork-generated Stable Dynamics Model6 Nov
  2. 2022Continual Learning from Demonstration of Robotics Skills14 Feb

Other references · 9

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018Neural Ordinary Differential Equationscited by 3,733
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  4. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,313
  5. 2019Continual learning with hypernetworkscited by 267
  6. 2020Learning Stable Deep Dynamics Modelscited by 110
  7. 2020Continual Model-Based Reinforcement Learning with Hypernetworkscited by 41
  8. 2020ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flowscited by 33
  9. 2023Principled Weight Initialization for Hypernetworkscited by 19

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworkscited by 6
  2. 2025On Understanding of the Dynamics of Model Capacity in Continual Learningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2021Learning from Successful and Failed Demonstrations via Optimization
  2. 2021Similarity-Aware Skill Reproduction based on Multi-Representational Learning from Demonstration
  3. 2024Consistency Matters: Defining Demonstration Data Quality Metrics in Robot Learning from Demonstration
  4. 2023Auto-LfD: Towards Closing the Loop for Learning from Demonstrations
  5. 2019Benchmark for Skill Learning from Demonstration: Impact of User Experience, Task Complexity, and Start Configuration on Performance
  6. 2026Can Vision-Language-Action Models Learn from Real-World Data Continually without Forgetting?
  7. 2024Learning from Demonstration with Implicit Nonlinear Dynamics Models
  8. 2018Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robot Skills