23 citations · 25 across the 3 of their papers we have counts for
4 papers
Distributed Value Function Approximation for Collaborative Multi-Agent Reinforcement Learning
Milos S. Stankovic, Marko Beko, Srdjan S. Stankovic
In this paper we propose several novel distributed gradient-based temporal difference algorithms for multi-agent off-policy learning of linear approximation of the value function i…
Distributed Time Synchronization for Networks with Random Delays and Measurement Noise
Milos S. Stankovic, Srdjan S. Stankovic, Karl Henrik Johansson
In this paper a new distributed asynchronous algorithm is proposed for time synchronization in networks with random communication delays, measurement noise and communication dropou…
Distributed Stochastic Approximation: Weak Convergence and Network Design
Miloš S. Stanković, Nemanja Ilić, Srdjan S. Stanković
This paper studies distributed stochastic approximation algorithms based on broadcast gossip on communication networks represented by digraphs. Weak convergence of these algorithms…
Distributed Blind Calibration via Output Synchronization in Lossy Sensor Networks
Miloš S. Stanković, Srđan S. Stanković, Karl Henrik Johansson
In this paper a novel distributed algorithm for blind macro calibration in sensor networks based on output synchronization is proposed. The algorithm is formulated as a set of grad…