Optimised Traffic Light Management Through Reinforcement Learning: Traffic State Agnostic Agent vs. Holistic Agent With Current V2I Traffic State Knowledge

Busch, Johannes V. S.; Latzko, Vincent; Reisslein, Martin; Fitzek, Frank H. P.

doi:10.1109/ojits.2020.3027518

Cited by 15 publications

(10 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Complementary to the aforementioned study [113] where TLC with varying portions of V2I enabled vehicles ranging from 0 to 100% at a single intersection, the authors of [114] examined the performance impact of traffic state information collected via V2I communication for road networks consisting of multiple intersections considering the extreme cases of 0% of V2I enabled vehicles in [113] (equivalent to their agnostic agent) and 100% of V2I enabled vehicles in [113] (equivalent to their holistic agent). The study's key contribution is a detailed comparison of a representative state-of-the-art agnostic DRL agent that is unaware of the current traffic state versus a representative state-of-the-art holistic DRL agent that is aware of the current traffic state.…”

Section: Traffic Light Controlmentioning

confidence: 99%

See 1 more Smart Citation

Deep reinforcement learning techniques for vehicular networks: Recent advances and future trends towards 6G

Mekrache

Bradai

Moulay

et al. 2022

Vehicular Communications

View full text Add to dashboard Cite

Employing machine learning into 6G vehicular networks to support vehicular application services is being widely studied and a hot topic for the latest research works in the literature. This article provides a comprehensive review of research works that integrated reinforcement and deep reinforcement learning algorithms for vehicular networks management with an emphasis on vehicular telecommunications issues. Vehicular networks have become an important research area due to their specific features and applications such as standardization, efficient traffic management, road safety, and infotainment. In such networks, network entities need to make decisions to maximize network performance under uncertainty. To achieve this goal, Reinforcement Learning (RL) can effectively solve decision-making problems. However, the state and action spaces are massive and complex in large-scale wireless networks. Hence, RL may not be able to find the best strategy in a reasonable time. Therefore, Deep Reinforcement Learning (DRL) has been developed to combine RL with Deep Learning (DL) to overcome this issue. In this survey, we first present vehicular networks and give a brief overview of RL and DRL concepts. Then we review RL and especially DRL approaches to address emerging issues in 6G vehicular networks. We finally discuss and highlight some unresolved challenges for further study.

show abstract

Section: Traffic Light Controlmentioning

confidence: 99%

“…They also compared a reward function that considers only the average vehicle velocity with a composite reward function that takes into account a weighted combination of the average vehicle velocity, vehicle flow rate, CO 2 emissions, and driver stress level. They found that the holistic system substantially [114].…”

Section: Traffic Light Controlmentioning

confidence: 99%

Deep reinforcement learning techniques for vehicular networks: Recent advances and future trends towards 6G

Mekrache

Bradai

Moulay

et al. 2022

Vehicular Communications

View full text Add to dashboard Cite

show abstract

“…Sparse reward settings are one of the obstacles for reinforcement learning [16]. That is, where the agent receives a reward only when meeting the target level.…”

Section: Figure 1: Reinforcement Learning Agent-environment Cyclementioning

confidence: 99%

“…The implementation of RL have been studied extensively to find the optimal traffic signal timing policy since the 1990s [1,5,16]. Earlier work was limited to Tabular Q-learning in RL.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Agent Reinforcement Learning for Optimizing Traffic Signal Timing

Salaymeh¹,

Schwiebert²,

Remias³

2021

Computer Science &Amp; Information Technology (CS &Amp; IT)

View full text Add to dashboard Cite

Designing efficient transportation systems is crucial to save time and money for drivers and for the economy as whole. One of the most important components of traffic systems are traffic signals. Currently, most traffic signal systems are configured using fixed timing plans, which are based on limited vehicle count data. Past research has introduced and designed intelligent traffic signals; however, machine learning and deep learning have only recently been used in systems that aim to optimize the timing of traffic signals in order to reduce travel time. A very promising field in Artificial Intelligence is Reinforcement Learning. Reinforcement learning (RL) is a data driven method that has shown promising results in optimizing traffic signal timing plans to reduce traffic congestion. However, model-based and centralized methods are impractical here due to the high dimensional state-action space in complex urban traffic network. In this paper, a model-free approach is used to optimize signal timing for complicated multiple four-phase signalized intersections. We propose a multi-agent deep reinforcement learning framework that aims to optimize traffic flow using data within traffic signal intersections and data coming from other intersections in a Multi-Agent Environment in what is called Multi-Agent Reinforcement Learning (MARL). The proposed model consists of state-of-art techniques such as Double Deep Q-Network and Hindsight Experience Replay (HER). This research uses HER to allow our framework to quickly learn on sparse reward settings. We tested and evaluated our proposed model via a Simulation of Urban MObility simulation (SUMO). Our results show that the proposed method is effective in reducing congestion in both peak and off-peak times.

show abstract