Cooperative multi-agent reinforcement learning models (CMRLM) for intelligent traffic control

Vidhate, Deepak A.; Kulkarni, Parag

doi:10.1109/icisim.2017.8122193

Cited by 21 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Daeho et al (10) predicted future traffic conditions and performed a cooperation control. Deepak et al (11) proposed cooperative multi-agent reinforcement learning-based models for traffic control optimization.…”

Section: Related Workmentioning

confidence: 99%

Proposal for Selecting a Cooperation Partner in Distributed Control of Traffic Signals using Deep Reinforcement Learning

Matsuta¹,

Kodama²,

Harada

2021

The Proceedings of the 8th International Conference on Intelligent Systems and Image Processing 2021

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Proposal for Selecting a Cooperation Partner in Distributed Control of Traffic Signals using Deep Reinforcement Learning

Matsuta¹,

Kodama²,

Harada

2021

The Proceedings of the 8th International Conference on Intelligent Systems and Image Processing 2021

View full text Add to dashboard Cite

“…A variety of different AI-based methods [54][55][56][57][58][59][60][61] were used for eliminating bottlenecks or to increase the throughput at the signalized intersections.…”

Section: Artificial Intelligence-based Approachesmentioning

confidence: 99%

“…Vidhate et al [56] and Genders et al [57] modeled TSC using the RL algorithm based on real-time traffic data whereas Liang et al [58] proposed a deep RL model to decide the TST and to control the cycle length of traffic signal based on the data collected through different sensors. Ozan et al [61] presented a modified RL algorithm that was based on Q-Learning.…”

Section: Artificial Intelligence-based Approachesmentioning

confidence: 99%

State-of-art review of traffic signal control methods: challenges and opportunities

Qadri

Gökçe

Öner

2020

Eur. Transp. Res. Rev.

105

View full text Add to dashboard Cite

Introduction Due to the menacing increase in the number of vehicles on a daily basis, abating road congestion is becoming a key challenge these years. To cope-up with the prevailing traffic scenarios and to meet the ever-increasing demand for traffic, the urban transportation system needs effective solution methodologies. Changes made in the urban infrastructure will take years, sometimes may not even be feasible. For this reason, traffic signal timing (TST) optimization is one of the fastest and most economical ways to curtail congestion at the intersections and improve traffic flow in the urban network. Purpose Researchers have been working on using a variety of approaches along with the exploitation of technology to improve TST. This article is intended to analyze the recent literature published between January 2015 and January 2020 for the computational intelligence (CI) based simulation approaches and CI-based approaches for optimizing TST and Traffic Signal Control (TSC) systems, provide insights, research gaps and possible directions for future work for researchers interested in the field. Methods In analyzing the complex dynamic behavior of traffic streams, simulation tools have a prominent place. Nowadays, microsimulation tools are frequently used in TST related researches. For this reason, a critical review of some of the widely used microsimulation packages is provided in this paper. Conclusion Our review also shows that approximately 77% of the papers included, utilizes a microsimulation tool in some form. Therefore, it seems useful to include a review, categorization, and comparison of the most commonly used microsimulation tools for future work. We conclude by providing insights into the future of research in these areas.

show abstract

“…The optimal policy is obtained by iterating the learning mechanism based on the reward from the environment or an established neural network to approximate the environment model by the critic-actor architecture [14], [15]. Hence in the multi-agent systems, the RL is widely applied [16], such as in traffic control [17], [18], mobile robots [19]- [21], resource management [22], [23].…”

Section: Related Workmentioning

confidence: 99%

Hidden Markov Random Field for Multi-Agent Optimal Decision in Top-Coal Caving

Yang

Lin

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Applying model-based learning for the optimal decision of the multi-agent system is not trivial due to the expensive price or even the impossibility of obtaining the ground truth for training the model of the complex environment. Such as learning the optimal action of hydraulic supports in the top-coal caving, the optimal action could not accessible as the ground truth of the corresponding state in the intricate processes. Regarding the latent ground truth as the hidden variable is an effective method in the hidden Markov model. This paper extends the hidden variable of ground truth to the multi-agent system and proposes the hidden Markov random field (HMRF) model with reinforcement learning for optimizing the action decision of the multi-agent. In the HMRF model, the input states and the output actions of the multi-agent are considered as an observable random field and a latent Markov random field, respectively. Based on the HMRF model, the optimal decision is inferred by the maximum posterior probability with the prior probability obtained by Q-learning. Meanwhile, the parameters of the HMRF model are estimated by the expectation maximum algorithm. In the experiment, the top-coal caving demonstrates the effectiveness of the proposed method that the recall of top-coal is improved prominently with a very small price of increasing the rock-rate. Furthermore, the proposed method is employed to deal with the predator-preys problem in the gym. The experiment result shows that the communication between agents by the HMRF increases the reward of the preys. INDEX TERMS Hidden Markov random field, optimal decision, multi-agent, top-coal caving.

show abstract

Cooperative multi-agent reinforcement learning models (CMRLM) for intelligent traffic control

Cited by 21 publications

References 16 publications

Proposal for Selecting a Cooperation Partner in Distributed Control of Traffic Signals using Deep Reinforcement Learning

Proposal for Selecting a Cooperation Partner in Distributed Control of Traffic Signals using Deep Reinforcement Learning

State-of-art review of traffic signal control methods: challenges and opportunities

Hidden Markov Random Field for Multi-Agent Optimal Decision in Top-Coal Caving

Contact Info

Product

Resources

About