Using Transfer Learning in an Ad Hoc Team
DOI:
https://doi.org//10.32628/CSEIT1952259Keywords:
Ad Hoc Teamwork, Transfer Learning, Multi Agent SystemsAbstract
In a practical scenario, we have a myriad of robotic systems; single and multi agent, not operating under any standard communication protocols. This is eminent from a point of view where independent robots can come together to achieve goals as a team. This problem is well defined in the domain of Ad Hoc Teamwork(AHT) which strives for a MAS wherein agents are heterogeneous, independent in their own respect and, as a whole accomplish goals that may be above any individual's capability. A key aspect is transfer learning which allows on the fly addition of team members. This paper shares development in transfer learning in the field of Ad Hoc Teamwork.
References
- David Silver, Aja Huang, Christopher J. Maddison, Arthur Guez, Laurent Sifre, Georgevan den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, MarcLanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever,Timothy Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, and Demis Hass-abis. Mastering the game of go with deep neural networks and tree search. Nature, 529:484–503, 2016
- Vivek Wadhwa and Alex Salkever.The Driver in the Driverless Car: How Our Technol-ogy Choices Will Create the Future. Berrett-Koehler Publishers, 1st edition, 2017. ISBN1626569711, 9781626569713.
- Samuel Barrett and Peter Stone. Cooperating with unknown teammates in complex domains:A robot soccer case study of ad hoc teamwork. InProceedings of the Twenty-Ninth AAAIConference on Artificial Intelligence, AAAI’15, pages 2010–2016. AAAI Press, 2015. ISBN0-262-51129-0.
- Sunghun Jung and Hyunsu Kim. Analysis of amazon prime air uav delivery service.Journalof Knowledge Information Technology and Systems, 12:253–266, 04 2017.
- S. Yue and S. Ozawa. A sequential multi-task learning neural network with metric-basedknowledge transfer. In2012 11th International Conference on Machine Learning and Appli-cations, volume 1, pages 671–674, Dec 2012. doi:10.1109/ICMLA.2012.125.
- T. Takano, H. Takase, H. Kawanaka, and S. Tsuruoka. Transfer method for reinforcementlearning in same transition model – quick approach and preferential exploration. In2011 10thInternational Conference on Machine Learning and Applications and Workshops, volume 1,pages 466–469, Dec 2011. doi:10.1109/ICMLA.2011.148.
- C. Chen, B. Jiang, and X. Jin. Parameter transfer extreme learning machine based on pro-jective model. In2018 International Joint Conference on Neural Networks (IJCNN), pages1–8, July 2018. doi:10.1109/IJCNN.2018.8489244.
- E. Chalmers, E. B. Contreras, B. Robertson, A. Luczak, and A. Gruber. Learning to predictconsequences as a method of knowledge transfer in reinforcement learning.IEEE Trans-actions on Neural Networks and Learning Systems, 29(6):2259–2270, June 2018. ISSN2162-237X. doi:10.1109/TNNLS.2017.2690910.
- Q. Chen, Y. Du, M. Xu, and C. Wang. Heteotl: An algorithm for heterogeneous online transferlearning. In2018 IEEE 30th International Conference on Tools with Artificial Intelligence(ICTAI), pages 350–357, Nov 2018. doi:10.1109/ICTAI.2018.00062.
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.