2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDSPTM-3.5
Paper Title Byzantine-Resilient Decentralized TD Learning with Linear Function Approximation
Authors Zhaoxian Wu, Sun Yat-Sen University, China; Han Shen, Tianyi Chen, Rensselaer Polytechnic Institute, United States; Qing Ling, Sun Yat-Sen University, China
SessionSPTM-3: Estimation, Detection and Learning over Networks 1
LocationGather.Town
Session Time:Tuesday, 08 June, 14:00 - 14:45
Presentation Time:Tuesday, 08 June, 14:00 - 14:45
Presentation Poster
Topic Signal Processing Theory and Methods: Signal Processing over Networks
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract This paper considers the policy evaluation problem in reinforcement learning with agents of a decentralized and directed network. The focus is on decentralized temporal-difference (TD) learning with linear function approximation in the presence of unreliable or even malicious agents, termed as Byzantine agents. In order to evaluate the quality of a fixed policy in a common environment, agents usually run decentralized TD($\lambda$) collaboratively. However, when some Byzantine agents behave adversarially, decentralized TD($\lambda$) is unable to learn an accurate linear approximation for the true value function. We propose a trimmed-mean based decentralized TD($\lambda$) algorithm to perform policy evaluation in this setting. We establish the finite-time convergence rate, as well as the asymptotic learning error that depends on the number of Byzantine agents. Numerical experiments corroborate the robustness of the proposed algorithm.