2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE) 2018
DOI: 10.1109/icite.2018.8492537
|View full text |Cite
|
Sign up to set email alerts
|

Deep Reinforcement Learning for Autonomous Traffic Light Control

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
23
0
2

Year Published

2019
2019
2023
2023

Publication Types

Select...
4
4
1

Relationship

1
8

Authors

Journals

citations
Cited by 49 publications
(25 citation statements)
references
References 5 publications
0
23
0
2
Order By: Relevance
“…In the TSC problem, two main approaches are used for state representation. The first is raw pixel data in the form of snapshots from the intersection, which require relatively more computation resources since the use of convolutional neural networks (CNN) [41,42]. The second is feature-based value vectors which contain information about each lane provided by simple detectors [43,44].…”
Section: State Representationmentioning
confidence: 99%
“…In the TSC problem, two main approaches are used for state representation. The first is raw pixel data in the form of snapshots from the intersection, which require relatively more computation resources since the use of convolutional neural networks (CNN) [41,42]. The second is feature-based value vectors which contain information about each lane provided by simple detectors [43,44].…”
Section: State Representationmentioning
confidence: 99%
“…The papers [22][23][24][25][26][27][28] are employed a type of artificial learning algorithm for solving the TST problem. Among these studies, Neural Networks, Adaptive Neuro-Fuzzy Inference System, Q-Learning, fuzzy logic, and Deep Reinforcement learning are the adapted machine learning algorithms.…”
Section: Artificial Intelligence-based Approachesmentioning
confidence: 99%
“…Among these studies, Neural Networks, Adaptive Neuro-Fuzzy Inference System, Q-Learning, fuzzy logic, and Deep Reinforcement learning are the adapted machine learning algorithms. Different objectives have been used in these studies including minimization of average delay [22,27], total travel time [24,25], average queue length [26], optimization of TST plan [23], and maximization of the flow rate [28].…”
Section: Artificial Intelligence-based Approachesmentioning
confidence: 99%
“…In more complex settings, higherorder coordination algorithms, such as coordination-graphs and game-theoretic methods, e.g., max-plus, coordinate the actions of multiple agents, e.g., [56]. Building on the seminal MARL studies [13], [52], [55], [57]- [61], recent studies have further substantially advanced MARL computational and decision making strategies, see [62]- [67]. General related computational frameworks for RL control applications have been explored for multi-objective decision modeling in [68] and for a hybrid fuzzy and RL control in [69].…”
Section: Related Workmentioning
confidence: 99%