ON PRIVATIZING POLICY EVALUATION IN MULTI-AGENT REINFORCEMENT LEARNING

Content Files

SP23-ECE499-Thesis-Zhou, Yichen.pdf

Permalink

https://hdl.handle.net/2142/124784

Title: ON PRIVATIZING POLICY EVALUATION IN MULTI-AGENT REINFORCEMENT LEARNING
Author(s): Zhou, Yichen
Issue Date: 2023-05-01
Keyword(s): privacy-preserving algorithm, agent reinforcement learning.
Date of Ingest: 2024-10-04T10:52:49-05:00
Abstract: We propose a privacy-preserving algorithm for policy evaluation in multiagent reinforcement learning. We consider the collaborative setting that each agent wants to learn the aggregate discount cost for a control policy, while protecting the privacy of local cost functions. We employ the notion of privacy via non-identifiability and propose the use of network correlated perturbations that cancel over the network to hide locally incurred cost at each time step from honest-but-curious adversaries while preserving the important part of environment structure, i.e. the aggregate cost. We show that our algorithm preserves the original finite time analysis result and protects the privacy of local cost functions under certain graph conditions.
Type of Resource: text
Genre of Resource: dissertation/thesis
Language: eng

The best of ECE undergraduate research