2018 IEEE Congress on Evolutionary Computation (CEC) 2018
DOI: 10.1109/cec.2018.8477713
|View full text |Cite
|
Sign up to set email alerts
|

Co-Adaptive Reinforcement Learning in Microscopic Traffic Systems

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
1
0
2

Year Published

2019
2019
2023
2023

Publication Types

Select...
2
1
1

Relationship

2
2

Authors

Journals

citations
Cited by 4 publications
(3 citation statements)
references
References 7 publications
0
1
0
2
Order By: Relevance
“…Liu et al, 2018). The co-learning problem of both classes of learning agents, traffic signals and drivers, with different goals (minimizing individual travel times vs minimizing the queues locally), different nature (driver agents learn in episodes that are asynchronous, while traffic light agents learn continuously (non-episodic)), and the nontrivial task of microscopic modelling and simulation (whose actions are highly coupled) is another area of research that was addressed (Lemos et al, 2018). In addition to these lines of research in this category, analyzing what specifically RL does differently (i.e.…”
Section: Methods' Contribution and Combinationmentioning
confidence: 99%
“…Liu et al, 2018). The co-learning problem of both classes of learning agents, traffic signals and drivers, with different goals (minimizing individual travel times vs minimizing the queues locally), different nature (driver agents learn in episodes that are asynchronous, while traffic light agents learn continuously (non-episodic)), and the nontrivial task of microscopic modelling and simulation (whose actions are highly coupled) is another area of research that was addressed (Lemos et al, 2018). In addition to these lines of research in this category, analyzing what specifically RL does differently (i.e.…”
Section: Methods' Contribution and Combinationmentioning
confidence: 99%
“…No trabalho de [Wiering 2000] foi um dos pioneiros a tratar motoristas e semáforos aprendendo simultaneamente. Em [Lemos et al 2018] foi proposta uma abordagem baseada em jogos repetidos (para a classe motorista) e jogos estocásticos (para os semáforos). Por se tratar de naturezas diversas de aprendizado, o artigo também discute os desafios encontrados em termos de AR.…”
Section: Aplicaçõesunclassified
“…E já existem muitos trabalhos com a proposta de usar comunicação veicular para substituir semáforos [1], [3], [4], [5], [6]. Liang et al [7] e Lemos et al [8] usam técnicas mais apuradas para fazer o controle semafórico, com o uso de técnicas da inteligência computacional. Em contraste, neste trabalho, o controle de interseçãoé analisado do ponto de vista de troca de mensagens, com o apoio de comunicação veicular em um cenário miniaturizado.…”
Section: Introductionunclassified