Resilient Distributed Parameter Estimation in Sensor Networks

no code implementations • 3 Jun 2023 • Jiaqi Yan, Kuo Li, Hideaki Ishii

In this paper, we study the problem of parameter estimation in a sensor network, where the measurements and updates of some sensors might be arbitrarily manipulated by adversaries.

Decentralized Multi-Agent Reinforcement Learning: An Off-Policy Method

no code implementations • 31 Oct 2021 • Kuo Li, Qing-Shan Jia

Furthermore, convergence analysis is given under the discrete-space case, which guarantees that the policy will be reinforced by alternating between the processes of policy evaluation and policy improvement.

Multi-agent Reinforcement Learning Q-Learning +2

An Actor-Critic Method for Simulation-Based Optimization

no code implementations • 31 Oct 2021 • Kuo Li, Qing-Shan Jia, Jiaqi Yan

We formulate the sampling process as a policy searching problem and give a solution from the perspective of Reinforcement Learning (RL).

Adversarial Attack Reinforcement Learning (RL)