Learning to Communicate in Wireless Channels

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.

  1. IEEE Access Paper Blind Interactive Learning of Modulation Schemes: Multi-Agent Cooperation Without Co-Design
    Anant Sahai*, Joshua Sanz*, Vignesh Subramanian*, Caryn Tran*, and Kailas Vodrahalli*
    IEEE Access, 2020
  2. Master’s Thesis Effect of Model Dissimilarity on Learning to Communicate in a Wireless Setting with Limited Information
    Effect of Model Dissimilarity on Learning to Communicate in a Wireless Setting with Limited Information
    Caryn Tran
    University of California, Berkeley, 2019
    M.S. thesis, EECS Department
  3. Allerton Paper Learning to Communicate with Limited Co-Design
    Anant Sahai*, Joshua Sanz*, Vignesh Subramanian*, Caryn Tran*, and Kailas Vodrahalli*
    In 2019 57th Annual Allerton Conference on Communication, Control, and Computing, 2019
  4. arXiv Preprint Learning to Communicate in a Noisy Environment
    Anant Sahai*, Joshua Sanz*, Vignesh Subramanian*, Caryn Tran*, and Kailas Vodrahalli*
    arXiv preprint arXiv:1910.09630, 2019