DOI: 10.29007/bdgn
|View full text |Cite
|
Sign up to set email alerts
|

Reinforcement Learning Agent under Partial Observability for Traffic Light Control in Presence of Gridlocks

Abstract: Bangkok is notorious for its chronic traffic congestion due to the rapid urbanization and the haphazard city plan. The Sathorn Road network area stands to be one of the most critical areas where gridlocks are a normal occurrence during rush hours. This stems from the high volume of demand imposed by the dense geographical placement of 3 big educational institutions and the insufficient link capacity with strict routes. Current solutions place heavy reliance on human traffic control expertises to prevent and di… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Publication Types

Select...
2
1

Relationship

0
3

Authors

Journals

citations
Cited by 3 publications
(2 citation statements)
references
References 6 publications
0
2
0
Order By: Relevance
“…The length of the collected traffic jam represents the traffic condition of every action step. Based on the study [9], we define the action step as an interval of 10 seconds. The observed state as S t = {o 1,t , .…”
Section: B State Formulationmentioning
confidence: 99%
“…The length of the collected traffic jam represents the traffic condition of every action step. Based on the study [9], we define the action step as an interval of 10 seconds. The observed state as S t = {o 1,t , .…”
Section: B State Formulationmentioning
confidence: 99%
“…In ( Zhang et al, 2018 ) state observability was analyzed in a vehicle-to-infrastructure (V2I) scenario, where the traffic signal agent detects approaching vehicles with Dedicated Short Range Communications (DSRC) technology under different rates. In ( Horsuwan & Aswakul, 2019 ) a scenario with partially observable state (only occupancy sensors available) was studied, however no comparisons with different state definitions or sensors were made. In ( Chu et al, 2019 ), Chu et al introduced Multiagent A2C in scenarios where different vehicle flows distributed in the network changed their insertion rates independently.…”
Section: Related Workmentioning
confidence: 99%