Traffic Light Control by Multiagent Reinforcement Learning Systems

Bakker, Bram; Whiteson, Shimon; Kester, Leon; Groen, Frans C. A.

doi:10.1007/978-3-642-11688-9_18

Cited by 63 publications

(32 citation statements)

References 19 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Although simple, similar networks have been used in other tra c experiments [3,4]. A single Grid City block measures 200 meters.…”

Section: Methodsmentioning

confidence: 99%

“…Tra c lights are probably the most prevalent means of controlling tra c. Other methods include stop signs and roundabouts. Although many tra c lights rely on simple fixed protocols, they are none-the-less a vital component of tra c management [4]. More advanced adaptive Urban Tra c Controllers (UTC), such as RHODES [17], OPAC [11] and SCOOT 1 , have been developed in an e↵ort to improve the performance of tra c lights [22,18].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

From Goods to Traffic: First Steps Toward an Auction-Based Traffic Signal Controller

Raphael

Maskell

Sklar

2015

Advances in Practical Applications of Agents, Multi-Agent Systems, and Sustainability: The PAAMS Collection

View full text Add to dashboard Buy / Rent full text

Abstract. Tra c congestion is a major issue that plagues many urban road networks large and small. Tra c engineers are now leaning towards Intelligent Tra c Systems as many physical changes to road networks are costly or infeasible. Multi-Agent Systems (MAS) have become a popular paradigm for intelligent solutions to tra c management problems. There are many MAS approaches to tra c management that utilise market mechanisms. In market-based approaches, drivers "pay" to use the roadways. However, a major issue with many of these solutions is that they require technology that, as yet, does not exist or is not widely available. For example, they rely on a special software agent that resides within the vehicle. This "vehicle agent" is responsible for participating in the market mechanism and communicating with the transportation infrastructure. In this paper, an auction-based tra c controller is proposed which exploits all the benefits of market mechanisms without the need for a vehicle agent. Experimental results show that such a controller is better at reducing delay and increasing throughput in a simulated city, as compared to fixed-time signal controllers.

show abstract

“…Although simple, similar networks have been used in other tra c experiments [3,4]. A single Grid City block measures 200 meters.…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

From Goods to Traffic: First Steps Toward an Auction-Based Traffic Signal Controller

Raphael

Maskell

Sklar

2015

Advances in Practical Applications of Agents, Multi-Agent Systems, and Sustainability: The PAAMS Collection

View full text Add to dashboard Buy / Rent full text

show abstract

“…Step 4：Agent calculate reward value t r based on equation (5)and update learning rate t a based on equation (6).…”

Section: A Collaborative Q-learning Algorithemmentioning

confidence: 99%

“…Since traffic control is fundamentally a problem of sequential decision making, and at the same time is a task that is too complex for straightforward computation of optimal solutions or effective hand-coded solutions, it is perhaps best suited to the framework ofMarkov Decision Processes (MDPs) and reinforcement learning (RL) or approximate dynamic programming (ADP), in which an agent learns from trial and error via interaction with its environment [5].…”

Section: Introductionmentioning

confidence: 99%

Multi-intersections traffic signal intelligent control using collaborative q-learning algorithm

Yan

Lin

et al. 2011

2011 Seventh International Conference on Natural Computation

View full text Add to dashboard Buy / Rent full text

Since congestion of traffic is ubiquitous in the modern city, optimizing the behavior of traffic lights for efficient traffic flow is a critically important goal. However，agents often select only locally optimal actions without coordinating their neighbor intersections. In this paper, an urban road traffic area-wide coordination control algorithm based on collaborative Qlearning is proposed. The agent model of traffic intersections is demonstrated. The algorithm substantially reduces average vehicular delay by using a collaborative Q-learning algorithm and can cooperative control of multiple intersections to achieve a near optimal control policy. The computer simulation results show that the control algorithm can effectively reduce the average delay time and play a very good control effect with multi-intersections, so the coordination method used in this paper is effective.

show abstract

“…Poorly designed phase plans may lead to additional delays, traffic jams and even accidents. Although many traffic signals rely on simple fixed protocols, they are nonetheless a vital component of traffic management [1]. Historically, finding the best signal timings involved using mathematical models of traffic behaviour to determine ideal settings [22].…”

Section: Introductionmentioning

confidence: 99%

An Intersection-Centric Auction-Based Traffic Signal Control Framework

Raphael

Sklar

Maskell

2017

Understanding Complex Systems

View full text Add to dashboard Buy / Rent full text

Vehicular traffic on urban road networks is of great interest to those who monitor air quality. Combustion emissions from transport vehicles are a major contributor of air pollution. More specifically, the release of fine particulate matter which has been linked to premature deaths. Travel and idle time are two factors that influence the amount of pollution generated by traffic. Reducing idle and travel times would have a positive impact on air quality. Thus, it is increasingly crucial to manage intersections effectively, particularly in congested cities and across a range of different types of traffic conditions. A variety of market-based multi-agent traffic management mechanisms have been proposed to improve traffic flow. In many of these systems drivers "pay" to gain access to favourable road ways (e.g., minimise travel time). A major obstacle in adopting many of these mechanisms is that the necessary communication infrastructure does not yet exist. They rely on vehicle-toinfrastructure and/or vehicle-to-vehicle communications. In this work, we propose a market-based mechanism which relies on existing technology (and in some places this technology is already in use). Experimental results show that our market-based approach is better at reducing idle and travel times as compared to fixed-time signal controllers.

show abstract

Traffic Light Control by Multiagent Reinforcement Learning Systems

Cited by 63 publications

References 19 publications

From Goods to Traffic: First Steps Toward an Auction-Based Traffic Signal Controller

From Goods to Traffic: First Steps Toward an Auction-Based Traffic Signal Controller

Multi-intersections traffic signal intelligent control using collaborative q-learning algorithm

An Intersection-Centric Auction-Based Traffic Signal Control Framework

Contact Info

Product

Resources

About