Developing multi-agent protocols for modulation, cooperation, and communication without co-design.
This body of work studies how agents can learn to communicate over noisy wireless channels, adapt modulation schemes interactively, and coordinate without a hand-designed protocol. It grew out of work with Professor Anant Sahai at UC Berkeley and the Berkeley Wireless Research Center.
@article{sahai2020blind,project={echo},publication_sort={2020-01},title={Blind Interactive Learning of Modulation Schemes: Multi-Agent Cooperation Without Co-Design},author={Sahai, Anant and Sanz, Joshua and Subramanian, Vignesh and Tran, Caryn and Vodrahalli, Kailas},journal={IEEE Access},volume={8},pages={63790--63820},year={2020},publisher={IEEE},doi={10.1109/ACCESS.2020.2984218},}
Master’s Thesis
Effect of Model Dissimilarity on Learning to Communicate in a Wireless Setting with Limited Information
@mastersthesis{tran2019effect,project={echo},publication_sort={2019-01},title={Effect of Model Dissimilarity on Learning to Communicate in a Wireless Setting with Limited Information},author={Tran, Caryn},school={University of California, Berkeley},year={2019},note={M.S. thesis, EECS Department},}
@inproceedings{sahai2019learning,project={echo},publication_sort={2019-02},title={Learning to Communicate with Limited Co-Design},author={Sahai, Anant and Sanz, Joshua and Subramanian, Vignesh and Tran, Caryn and Vodrahalli, Kailas},booktitle={2019 57th Annual Allerton Conference on Communication, Control, and Computing},doi={10.1109/ALLERTON.2019.8919749},year={2019},organization={IEEE}}
@article{sahai2019learningnoise,project={echo},publication_sort={2019-01},title={Learning to Communicate in a Noisy Environment},author={Sahai, Anant and Sanz, Joshua and Subramanian, Vignesh and Tran, Caryn and Vodrahalli, Kailas},journal={arXiv preprint arXiv:1910.09630},url={https://arxiv.org/abs/1910.09630},year={2019}}