Filters








949 Hits in 3.9 sec

Reinforcement Learning forTrueAdaptive Traffic Signal Control

Baher Abdulhai, Rob Pringle, Grigoris J. Karakoulas
2003 Journal of transportation engineering  
This paper contains an introduction to Q-learning, a simple yet powerful reinforcement learning algorithm, and presents a case study involving application to traffic signal control.  ...  Reinforcement learning, an artificial intelligence approach undergoing development in the machinelearning community, offers key advantages in this regard.  ...  Acknowledgments The second writer wishes to acknowledge the financial assistance provided by the Natural Science and Engineering Research Council of Canada and the University of Toronto.  ... 
doi:10.1061/(asce)0733-947x(2003)129:3(278) fatcat:ocpavsaih5h57l2hqz2kbjslpy

Neural Networks for Real-Time Traffic Signal Control

D. Srinivasan, M.C. Choy, R.L. Cheu
2006 IEEE transactions on intelligent transportation systems (Print)  
This paper adopts the multiagent system approach to develop distributed unsupervised traffic responsive signal control models, where each agent in the system is a local traffic signal controller for one  ...  Real-time traffic signal control is an integral part of the urban traffic control system, and providing effective real-time traffic signal control for a large complex traffic network is an extremely challenging  ...  ACKNOWLEDGMENT The authors would like to thank the Land Transportation Authority of Singapore for providing data necessary for the simulation modeling.  ... 
doi:10.1109/tits.2006.874716 fatcat:3lgn75iyhbagjmyujzmexzyx6m

Multiagent Decision Making and Learning in Urban Environments

Akshat Kumar
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
In this paper, I will overview some of our recent contributions towards developing planning and reinforcement learning strategies to address several such challenges present in large-scale urban multiagent  ...  In addition, accurate domain models need to be learned from data that is often noisy and available only at an aggregate level.  ...  Acknowledgments I thank my collaborators and mentors. I also thank the UNi-CEN center at SMU (https://unicen.smu.edu.sg/) for providing a conducive environment.  ... 
doi:10.24963/ijcai.2019/895 dblp:conf/ijcai/Kumar19 fatcat:m7pe5nx2pfehndnmbyvk2hyete

Multiagent Traffic Management: Opportunities for Multiagent Learning [chapter]

Kurt Dresner, Peter Stone
2006 Lecture Notes in Computer Science  
We believe that the domain created by this mechanism and protocol presents many opportunities for multiagent learning on the parts of both classes of agents.  ...  Traffic congestion is one of the leading causes of lost productivity and decreased standard of living in urban settings.  ...  The true multiagent learning opportunities lie in the vehicles.  ... 
doi:10.1007/11691839_7 fatcat:742y6cmrazfinf4pxa4q5m3lky

Reports on the 2018 AAAI Spring Symposium Series

Christopher Amato, Haitham Bou Ammar, Elizabeth Churchill, Erez Karpas, Takashi Kido, Mike Kuniavsky, W. F. Lawless, Francesca Rossi, Frans A. Oliehoek, Stephen Russell, Keiki Takadama, Siddharth Srivastava (+5 others)
2018 The AI Magazine  
, and Learning in Robotics; Learning, Inference, and Control of Multi-Agent Systems.  ...  Cognitive Bias and Humanity for Well-Being AI; Data Efficient Reinforcement Learning; The Design of the User Experience for Artificial Intelligence (the UX of AI); Integrated Representation, Reasoning  ...  Learning, Inference, and Control of MultiAgent Systems Agents are and will be deployed in a range of environments.  ... 
doi:10.1609/aimag.v39i4.2824 fatcat:qt3z2vh7vjetpiecy7c3xayb4e

:{unav)

Peter Stone, Manuela Veloso
2012 Autonomous Robots  
Additional opportunities for applying machine learning to MAS are highlighted and robotic soccer is presented as an appropriate testbed for MAS.  ...  Multiagent Systems (MAS) is the emerging subfield of AI that aims to provide both principles for construction of complex systems involving multiple agents and mechanisms for coordination of independent  ...  issues, techniques, and learning opportunities for communicating multiagent systems as reflected in the literature.  ... 
doi:10.1023/a:1008942012299 fatcat:4tjofcxn4jdkdn5ey7oe2oi2xm

An agent-based approach for road pricing: system-level performance and implications for drivers

Anderson Rocha Tavares, Ana LC Bazzan
2014 Journal of the Brazilian Computer Society  
Methods: We model traffic as a multiagent system in which link manager agents employ a reinforcement learning scheme to determine road pricing policies in a road network.  ...  Conclusions: Our experiments showed that the adoption of reinforcement learning for determining road pricing policies is a promising approach, even with limitations in the driver agent and link manager  ...  Acknowledgements The authors would like to thank the anonymous reviewers for their valuable comments and suggestions. We also thank Gabriel Ramos for his help with the  ... 
doi:10.1186/1678-4804-20-15 fatcat:udp2wfirgbed5dkvqb3v5xs2ti

Resource Abstraction for Reinforcement Learning in Multiagent Congestion Problems [article]

Kleanthis Malialis and Sam Devlin and Daniel Kudenko
2019 arXiv   pre-print
Multiagent reinforcement learning (MARL) is a promising candidate for dealing with this emerging complexity by providing an autonomous and distributed solution to these problems.  ...  congestion problems in large-scale scenarios involving up to 1000 reinforcement learning agents.  ...  BACKGROUND Reinforcement Learning Reinforcement learning is a paradigm in which an active decision-making agent interacts with its environment and learns from reinforcement, that is, a numeric feedback  ... 
arXiv:1903.05431v1 fatcat:xr3trgzxtfabvdkm5br3zmbjmu

Prosocial Norm Emergence in Multiagent Systems [article]

Mehdi Mashayekhi
2022 arXiv   pre-print
Multiagent systems provide a basis for developing systems of autonomous entities and thus find application in a variety of domains.  ...  Specifically, the social structure of a multiagent system can be reflected in the social norms among its members.  ...  We would also like to thank the anonymous reviewers for their careful reading of our manuscript and their insightful comments and suggestions.  ... 
arXiv:2012.14581v2 fatcat:pwow2hlfzncanepktzmv2eqkee

Prosocial Norm Emergence in Multiagent Systems

Mehdi Mashyekhi, Nirav Ajmeri, George F. List, Munindar P. Singh
2022 ACM Transactions on Autonomous and Adaptive Systems  
Multiagent systems provide a basis for developing systems of autonomous entities and thus find application in a variety of domains.  ...  Specifically, the social structure of a multiagent system can be reflected in the social norms among its members.  ...  We would also like to thank the anonymous reviewers for their careful reading of our manuscript and their insightful comments and suggestions.  ... 
doi:10.1145/3540202 fatcat:hcesditw65f4poiamif66tdvam

From Reactive Robotics to Situated Multiagent Systems [chapter]

Danny Weyns, Tom Holvoet
2006 Lecture Notes in Computer Science  
The notion of environment exceeds specific types of agency, and as such offers opportunities for synergetic research in the interest of multiagent systems in general.  ...  Today, it is quite obvious that the environment offers opportunities and challenges for all types of agency.  ...  The notion of environment exceeds specific types of agency, and as such offers opportunities for synergetic research in the interest of multiagent systems in general.  ... 
doi:10.1007/11759683_5 fatcat:gdwjoayqjbai7nb6vh2hyorpc4

Improving Urban Mobility: using artificial intelligence and new technologies to connect supply and demand [article]

Ana L. C. Bazzan
2022 arXiv   pre-print
in the vehicular traffic.  ...  In this panorama, artificial intelligence plays an important role, especially with the advances in machine learning that translates in the use of computational vision, connected and autonomous vehicles  ...  More recently, AI and multiagent systems techniques have been employed, especially in connection with reinforcement learning.  ... 
arXiv:2204.03570v1 fatcat:v4geolku7bd6nb5j4in7wsdf7i

Transfer Learning versus Multiagent Learning regarding Distributed Decision-Making in Highway Traffic

Mark Schutera, Niklas Goby, Dirk Neumann, Markus Reischl
2018 International Joint Conference on Artificial Intelligence  
In the first step traffic agents are trained by means of a deep reinforcement learning approach, being deployed inside an elitist evolutionary algorithm for hyperparameter search.  ...  Transportation and traffic are currently undergoing a rapid increase in terms of both scale and complexity.  ...  Jochen Abhau and Dr. Stefan Elser from Research and Development, as well as the whole Data Science Team at ZF Friedrichshafen AG, for supporting this research.  ... 
dblp:conf/ijcai/SchuteraG0R18 fatcat:kpbploe6nvaqvnwf6qzlbhgtva

Improvement of the road traffic management by an ant-hierarchical fuzzy system

Habib M. Kammoun, Ilhem Kallel, Adel M. Alimi, Jorge Casillas
2011 2011 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems (CIVTS) Proceedings  
Series of simulations, under a multiagent platform, allow us to discuss the improvement of the global road traffic quality in terms of time, fluidity, and adaptability.  ...  In view of dynamicity on road networks and the sharp increase of traffic jam states, the road traffic management becomes more complex.  ...  This encourages us to go on further and to develop a hierarchical fuzzy system, in a cooperative multiagent system, for traffic management.  ... 
doi:10.1109/civts.2011.5949535 dblp:conf/civts/KammounKAC11 fatcat:2h7ro2vuufewljaeohtwvwu4ra

Multirobot Coordination for Space Exploration

Logan Yliniemi, Adrian K. Agogino, Kagan Tumer
2014 The AI Magazine  
Instead, this article examines tackling this problem through the use of coordinated reinforcement learning: rather than being programmed what to do, the rovers iteratively learn through trial and error  ...  To allow for coordination, yet allow each agent to learn and act independently, we employ state-of-the-art reward shaping techniques.  ...  Multiagent coordination is hard Being able to automatically learn intelligent control policies for autonomous systems is an exciting prospect for space exploration.  ... 
doi:10.1609/aimag.v35i4.2556 fatcat:ztd2azjzyvbpjauv62qdnji4hm
« Previous Showing results 1 — 15 out of 949 results