Autonomous Car Racing in Simulation Environment Using Deep Reinforcement Learning

Kivanc Guckiran; Bulent Bolat

doi:10.1109/ASYU48272.2019.8946332

Autonomous Car Racing in Simulation Environment Using Deep Reinforcement Learning

Kivanc Guckiran, Bulent Bolat

Yildiz Technical University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

18 Citations (Scopus)

Abstract

Self-Driving Cars are, currently a hot topic throughout the globe thanks to the advancements in Deep Learning techniques on computer vision problems. Since driving simulations are fairly important before real life autonomous implementations, there are multiple driving-racing simulations for testing purposes. The Open Racing Car Simulation (TORCS) is a highly portable open source car racing-self-driving-simulation. While it can be used as a game in which human players compete with scripted agents, TORCS provides observation and action API to develop an artificial intelligence agent. This study explores near-optimal Deep Reinforcement Learning agents for TORCS environment using Soft Actor-Critic and Rainbow DQN algorithms, exploration and generalization techniques.

Original language	English
Title of host publication	Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728128689
DOIs	https://doi.org/10.1109/ASYU48272.2019.8946332
Publication status	Published - Oct 2019
Externally published	Yes
Event	2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019 - Izmir, Turkey Duration: 31 Oct 2019 → 2 Nov 2019

Publication series

Name	Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019

Conference

Conference	2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019
Country/Territory	Turkey
City	Izmir
Period	31/10/19 → 2/11/19

Bibliographical note

Publisher Copyright:
© 2019 IEEE.

Keywords

Deep Reinforcement Learning
Self-Driving Car
TORCS

Access to Document

10.1109/ASYU48272.2019.8946332

Cite this

Guckiran, K., & Bolat, B. (2019). Autonomous Car Racing in Simulation Environment Using Deep Reinforcement Learning. In Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019 Article 8946332 (Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ASYU48272.2019.8946332

Guckiran, Kivanc ; Bolat, Bulent. / Autonomous Car Racing in Simulation Environment Using Deep Reinforcement Learning. Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019).

@inproceedings{0073df2bd31f432bbf5c1c54e43fc269,

title = "Autonomous Car Racing in Simulation Environment Using Deep Reinforcement Learning",

abstract = "Self-Driving Cars are, currently a hot topic throughout the globe thanks to the advancements in Deep Learning techniques on computer vision problems. Since driving simulations are fairly important before real life autonomous implementations, there are multiple driving-racing simulations for testing purposes. The Open Racing Car Simulation (TORCS) is a highly portable open source car racing-self-driving-simulation. While it can be used as a game in which human players compete with scripted agents, TORCS provides observation and action API to develop an artificial intelligence agent. This study explores near-optimal Deep Reinforcement Learning agents for TORCS environment using Soft Actor-Critic and Rainbow DQN algorithms, exploration and generalization techniques.",

keywords = "Deep Reinforcement Learning, Self-Driving Car, TORCS",

author = "Kivanc Guckiran and Bulent Bolat",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019 ; Conference date: 31-10-2019 Through 02-11-2019",

year = "2019",

month = oct,

doi = "10.1109/ASYU48272.2019.8946332",

language = "English",

series = "Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019",

address = "United States",

}

Guckiran, K & Bolat, B 2019, Autonomous Car Racing in Simulation Environment Using Deep Reinforcement Learning. in Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019., 8946332, Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019, Institute of Electrical and Electronics Engineers Inc., 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019, Izmir, Turkey, 31/10/19. https://doi.org/10.1109/ASYU48272.2019.8946332

Autonomous Car Racing in Simulation Environment Using Deep Reinforcement Learning. / Guckiran, Kivanc; Bolat, Bulent.
Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8946332 (Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Autonomous Car Racing in Simulation Environment Using Deep Reinforcement Learning

AU - Guckiran, Kivanc

AU - Bolat, Bulent

PY - 2019/10

Y1 - 2019/10

N2 - Self-Driving Cars are, currently a hot topic throughout the globe thanks to the advancements in Deep Learning techniques on computer vision problems. Since driving simulations are fairly important before real life autonomous implementations, there are multiple driving-racing simulations for testing purposes. The Open Racing Car Simulation (TORCS) is a highly portable open source car racing-self-driving-simulation. While it can be used as a game in which human players compete with scripted agents, TORCS provides observation and action API to develop an artificial intelligence agent. This study explores near-optimal Deep Reinforcement Learning agents for TORCS environment using Soft Actor-Critic and Rainbow DQN algorithms, exploration and generalization techniques.

AB - Self-Driving Cars are, currently a hot topic throughout the globe thanks to the advancements in Deep Learning techniques on computer vision problems. Since driving simulations are fairly important before real life autonomous implementations, there are multiple driving-racing simulations for testing purposes. The Open Racing Car Simulation (TORCS) is a highly portable open source car racing-self-driving-simulation. While it can be used as a game in which human players compete with scripted agents, TORCS provides observation and action API to develop an artificial intelligence agent. This study explores near-optimal Deep Reinforcement Learning agents for TORCS environment using Soft Actor-Critic and Rainbow DQN algorithms, exploration and generalization techniques.

KW - Deep Reinforcement Learning

KW - Self-Driving Car

KW - TORCS

UR - http://www.scopus.com/inward/record.url?scp=85078338142&partnerID=8YFLogxK

U2 - 10.1109/ASYU48272.2019.8946332

DO - 10.1109/ASYU48272.2019.8946332

M3 - Conference contribution

AN - SCOPUS:85078338142

T3 - Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019

BT - Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019

Y2 - 31 October 2019 through 2 November 2019

ER -

Guckiran K, Bolat B. Autonomous Car Racing in Simulation Environment Using Deep Reinforcement Learning. In Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8946332. (Proceedings - 2019 Innovations in Intelligent Systems and Applications Conference, ASYU 2019). doi: 10.1109/ASYU48272.2019.8946332

Autonomous Car Racing in Simulation Environment Using Deep Reinforcement Learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this