Challenges and Opportunities of Applying Reinforcement Learning to Autonomous Racing

被引：6

作者：

Wurman, Peter R. ^{[1
]}

Stone, Peter ^{[2
,3
]}

Spranger, Michael ^{[4
]}

机构：

[1] Sony AI, Boston, MA 02116 USA

[2] Sony AI, Austin, TX 78712 USA

[3] Univ Texas Austin, Austin, TX 78712 USA

[4] Sony AI, Tokyo 1076032, Japan

来源：

IEEE INTELLIGENT SYSTEMS | 2022年 / 37卷 / 03期

关键词：

Process control; Reinforcement learning; Games; Complexity theory; Intelligent systems; Autonomous vehicles; LEVEL;

D O I：

10.1109/MIS.2022.3184427

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Simulated motorsports are an exciting environment in which to explore the power and limitations of deep reinforcement learning. Racing requires precise control of a vehicle that is operating at its traction limits while competing wheel-to-wheel with other drivers. We recently demonstrated an agent that can beat the best drivers in the world at the racing game Gran Turismo. In this article, we briefly discuss some of the lessons learned and some of the remaining open research challenges.

引用

页码：20 / 23

页数：4

共 9 条

[1] Berner C., 2019, ARXIV
[2] Betz J., 2022, ARXIV
[3] Brockman G, 2016, Arxiv, DOI [arXiv:1606.01540, DOI 10.48550/ARXIV.1606.01540]
[4] DeepStack: Expert-level artificial intelligence in heads-up no-limit poker
Moravcik, Matej
Schmid, Martin
Burch, Neil
Lisy, Viliam
Morrill, Dustin
Bard, Nolan
Davis, Trevor
Waugh, Kevin
Johanson, Michael
Bowling, Michael
[J]. SCIENCE, 2017, 356 (6337) : 508 - +
[5] Puterman ML., 1994, Markov decision processes: discrete stochastic dynamic programming. Series in probability and statistics, DOI [10.1002/9780470316887, DOI 10.1002/9780470316887]
[6] Mastering the game of Go with deep neural networks and tree search
Silver, David
Huang, Aja
Maddison, Chris J.
Guez, Arthur
Sifre, Laurent
van den Driessche, George
Schrittwieser, Julian
Antonoglou, Ioannis
Panneershelvam, Veda
Lanctot, Marc
Dieleman, Sander
Grewe, Dominik
Nham, John
Kalchbrenner, Nal
Sutskever, Ilya
Lillicrap, Timothy
Leach, Madeleine
Kavukcuoglu, Koray
Graepel, Thore
Hassabis, Demis
[J]. NATURE, 2016, 529 (7587) : 484 - +
[7] Sutton R.S., 2005, IEEE Trans. Neural Netw., V16, P285
[8] Grandmaster level in StarCraft II using multi-agent reinforcement learning
Vinyals, Oriol
Babuschkin, Igor
Czarnecki, Wojciech M.
Mathieu, Michael
Dudzik, Andrew
Chung, Junyoung
Choi, David H.
Powell, Richard
Ewalds, Timo
Georgiev, Petko
Oh, Junhyuk
Horgan, Dan
Kroiss, Manuel
Danihelka, Ivo
Huang, Aja
Sifre, Laurent
Cai, Trevor
Agapiou, John P.
Jaderberg, Max
Vezhnevets, Alexander S.
Leblond, Remi
Pohlen, Tobias
Dalibard, Valentin
Budden, David
Sulsky, Yury
Molloy, James
Paine, Tom L.
Gulcehre, Caglar
Wang, Ziyu
Pfaff, Tobias
Wu, Yuhuai
Ring, Roman
Yogatama, Dani
Wunsch, Dario
McKinney, Katrina
Smith, Oliver
Schaul, Tom
Lillicrap, Timothy
Kavukcuoglu, Koray
Hassabis, Demis
Apps, Chris
Silver, David
[J]. NATURE, 2019, 575 (7782) : 350 - +
[9] Outracing champion Gran Turismo drivers with deep reinforcement learning
Wurman, Peter R.
Barrett, Samuel
Kawamoto, Kenta
MacGlashan, James
Subramanian, Kaushik
Walsh, Thomas J.
Capobianco, Roberto
Devlic, Alisa
Eckert, Franziska
Fuchs, Florian
Gilpin, Leilani
Khandelwal, Piyush
Kompella, Varun
Lin, HaoChih
MacAlpine, Patrick
Oller, Declan
Seno, Takuma
Sherstan, Craig
Thomure, Michael D.
Aghabozorgi, Houmehr
Barrett, Leon
Douglas, Rory
Whitehead, Dion
Duerr, Peter
Stone, Peter
Spranger, Michael
Kitano, Hiroaki
[J]. NATURE, 2022, 602 (7896) : 223 - +

← 1 →