Byzantine-Resilient Decentralized Policy Evaluation With Linear Function Approximation

DOI10.1109/TSP.2021.3090952MaRDI QIDQ5103678zbMATH OpenOpenAlexFDO

Authors Zhaoxian Wu, Han Shen, Tianyi Chen, Qing Ling

Publication date 23 September 2022

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/tsp.2021.3090952

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Recommendations

• Multiagent Fully Decentralized Value Function Learning With Linear Convergence Rates
• Byzantine-Resilient Multiagent Optimization
• Finite-time performance of distributed temporal-difference learning with linear function approximation
• Distributed Policy Evaluation Under Multiple Behavior Strategies
• Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach
• Optimal and approximate Q-value functions for decentralized POMDPS
• Provably efficient reinforcement learning in decentralized general-sum Markov games
• A simplified convergence theory for Byzantine resilient stochastic gradient descent
• Distributed policy evaluation via inexact ADMM in multi-agent reinforcement learning
• scientific article; zbMATH DE number 5547972

Cited in

(3)

• Multiagent Fully Decentralized Value Function Learning With Linear Convergence Rates
• Graph-theoretic approaches for analyzing the resilience of distributed control systems: a tutorial and survey
• Resilient fully-distributed reinforcement learning for UAV swarms against general Byzantine attacks

This page was built for publication: Byzantine-Resilient Decentralized Policy Evaluation With Linear Function Approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5103678)