Papers
Topics
Authors
Recent
Detailed Answer
Quick Answer
Concise responses based on abstracts only
Detailed Answer
Well-researched responses based on abstracts and relevant paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses
Gemini 2.5 Flash
Gemini 2.5 Flash 37 tok/s
Gemini 2.5 Pro 41 tok/s Pro
GPT-5 Medium 10 tok/s Pro
GPT-5 High 15 tok/s Pro
GPT-4o 84 tok/s Pro
Kimi K2 198 tok/s Pro
GPT OSS 120B 448 tok/s Pro
Claude Sonnet 4 31 tok/s Pro
2000 character limit reached

Effect of Optimizer, Initializer, and Architecture of Hypernetworks on Continual Learning from Demonstration (2401.00524v1)

Published 31 Dec 2023 in cs.RO and cs.LG

Abstract: 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.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (16)
  1. A. Billard, S. Calinon, and R. Dillmann, “Learning from humans,” Springer Handbook of Robotics, 2nd Ed., 2016.
  2. S. Auddy, J. Hollenstein, M. Saveriano, A. Rodríguez-Sánchez, and J. Piater, “Continual learning from demonstration of robotics skills,” Robotics and Autonomous Systems, vol. 165, p. 104427, 2023. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0921889023000660
  3. S. Auddy, J. Hollenstein, M. Saveriano, A. Rodríguez-Sánchez, and J. Piater, “Scalable and efficient continual learning from demonstration via hypernetwork-generated stable dynamics model,” arXiv preprint arXiv:2311.03600, 2023.
  4. J. Z. Kolter and G. Manek, “Learning stable deep dynamics models,” Advances in Neural Information Processing Systems, vol. 32, pp. 11 128–11 136, 2019.
  5. Y. Huang, K. Xie, H. Bharadhwaj, and F. Shkurti, “Continual model-based reinforcement learning with hypernetworks,” in 2021 IEEE International Conference on Robotics and Automation (ICRA).   IEEE, 2021, pp. 799–805.
  6. P. Schöpf, S. Auddy, J. Hollenstein, and A. Rodriguez-Sanchez, “Hypernetwork-ppo for continual reinforcement learning,” in Deep Reinforcement Learning Workshop NeurIPS 2022, 2022.
  7. G. I. Parisi, R. Kemker, J. L. Part, C. Kanan, and S. Wermter, “Continual lifelong learning with neural networks: A review,” Neural Networks, vol. 113, pp. 54–71, 2019.
  8. O. Chang, L. Flokas, and H. Lipson, “Principled weight initialization for hypernetworks,” in 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020.   OpenReview.net, 2020. [Online]. Available: https://openreview.net/forum?id=H1lma24tPB
  9. K. He, X. Zhang, S. Ren, and J. Sun, “Delving deep into rectifiers: Surpassing human-level performance on imagenet classification,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1026–1034.
  10. J. Urain, M. Ginesi, D. Tateo, and J. Peters, “Imitationflow: Learning deep stable stochastic dynamic systems by normalizing flows,” in 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   IEEE, 2020, pp. 5231–5237.
  11. R. T. Chen, Y. Rubanova, J. Bettencourt, and D. Duvenaud, “Neural ordinary differential equations,” in Proceedings of the 32nd International Conference on Neural Information Processing Systems, 2018, pp. 6572–6583.
  12. J. von Oswald, C. Henning, J. Sacramento, and B. F. Grewe, “Continual learning with hypernetworks,” in International Conference on Learning Representations (ICLR), 2019.
  13. T. Tieleman and G. Hinton, “6.5-rmsprop coursera: Neural networks for machine learning university of toronto,” Tech. Rep., 2012.
  14. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
  15. J. Duchi, E. Hazan, and Y. Singer, “Adaptive subgradient methods for online learning and stochastic optimization.” Journal of machine learning research, vol. 12, no. 7, 2011.
  16. X. Glorot and Y. Bengio, “Understanding the difficulty of training deep feedforward neural networks,” in Proceedings of the thirteenth international conference on artificial intelligence and statistics.   JMLR Workshop and Conference Proceedings, 2010, pp. 249–256.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up
Lightbulb On Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now