Multiagent Reinforcement Learning for Urban Traffic Control Using Coordination Graphs

By Lior Kuyer, Shimon Whiteson, Bram Bakker, Nikos A. Vlassis. 2008

258 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Control and Systems Engineering, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Control and Systems Engineering

In Molecular Biology

Citations in the corpus

Value-Decomposition Networks For Cooperative Multi-Agent Learning (2017, methodology): “Our approach works with only a team reward, and learns the value-decomposition autonomously from experience, and it similarly differs from the approach with coordination graphs (Guestrin et al., 2002) and the max-plus algorithm (Kuyer et al., 2008; van der Pol and Oliehoek, 2016).”
Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning (2017, background): “However, many real-world problems, such as network packet delivery (Ye et al., 2015), rubbish removal (Makar et al., 2001), and urban trafﬁc control (Kuyer et al., 2008; Van der Pol & Oliehoek, 2016), are naturally modeled as cooperative multi-agent systems.”
Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems (2012, background): “…several successful applications of decentralized RL have been reported, like the control of a robotic manipulator (Busoniu, Babuska, & Schutter, 2006), multi-robot cooperative transportation tasks (Wang & de Silva, 2008) or urban trafﬁc control (Kuyer, Whiteson, Bakker, & Vlassis, 2008).”
A review on agent-based technology for traffic and transportation (2013, unknown): “The work of Kuyer et al .”
CoLight: Learning Network-level Cooperation for Traffic Signal Control (2019, background): “For example, studies [16, 24] have proposed to jointly model two adjacent intersections.”
Distributed Multiagent Coordinated Learning for Autonomous Driving in Highways Based on Dynamic Coordination Graphs (2020, background): “multi-robot systems and resource management to automated trading [49]–[52].”
Toward A Thousand Lights: Decentralized Deep Reinforcement Learning for Large-Scale Traffic Signal Control (2020, methodology): “Firstly, methods that resort to centralized optimization of coordinated agents (Prashanth and Bhatna-gar 2011; Kuyer et al. 2008; Van der Pol and Oliehoek 2016) cannot satisfy scalability , due to the combinatorially-large joint action space.”
A Concise Introduction to Decentralized POMDPs (2016, methodology): “A number of papers address such problems from the learning perspective [Wiering, 2000, Wiering et al., 2004, Bazzan, 2005, Kuyer et al., 2008, Bazzan et al., 2010].”
Exploiting Agent and Type Independence in Collaborative Graphical Bayesian Games (2011, background): “PLUS will converge.8 However, experimental results have demonstrated that it works well in practice even when cycles are present (Kschischang et al., 2001; Kok and Vlassis, 2006; Kuyer et al., 2008).”
Coordinated Deep Reinforcement Learners for Traffic Light Control (2016, methodology): “As a baseline, we use an earlier algorithm by Wiering [23] and its multi-agent extension by Kuyer et al [8].”
A Survey on Traffic Signal Control Methods (2019, methodology): “rol Methods • :19 Table 7. Model-based and model-free methods in RL-based traffic signal control methods References Model-based methods [Cahill et al. 2010; Khamis and Gomaa 2012; Khamis et al. 2012; Kuyer et al. 2008; Steingrover et al. 2005; Wiering 2000; Wiering et al. 2004a,b] Model-free methods”