This website is dedicated to the editorial and author-support activities of the journal 'Artificial Intelligence', usually referred to as the AIJ. It does not document the publisher's activities (but see the link to Elsevier's website at the top right of this page, "AIJ@Elsevier").
FREE ACCESS TO ARTIFICIAL INTELLIGENCE JOURNAL IS RE-ESTABLISHED!!
FOR FURTHER INFORMATION PLEASE SEE http://aij.ijcai.org/free-access-to-the-ai-journal
The editorial process is organized by the Artificial Intelligence Journal Division (AIJD) of IJCAI.
All submissions should be made via the Elsevier's Editorial System. Submission via email is not possible.
THE SUMMER CALL FOR FUNDING IS NOW COMPLETED.
CLICK HERE TO VIEW THE RESULTS.
Printed version out now of the
Special Issue on Autonomous Agents Modelling Other Agents,
Edited by Stefano V. Albrecht, Peter Stone, Michael P. Wellman
THE NOMINATIONS FOR 2020 CLASSIC AND PROMINENT PAPER AWARDS is open May 11 - June 1.
Please nominate using this link: https://easychair.org/conferences/?conf=aij20awards
All papers can be found online on the Elseveier webpage: https://www.sciencedirect.com/journal/artificial-intelligence/issues
Full information about the Classic and prominent paper Awards can be found on the AIJ Award Page.
THE WINNERS OF THE 2019 CLASSIC AND PROMINENT PAPER AWARDS
2019 Classic AIJ Paper Award
Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
RS Sutton, D Precup, S Singh - Artificial intelligence, 1999 - Elsevier
URL: https://www.sciencedirect.com/science/article/pii/S0004370299000521
This is the seminal paper on options, a widely used framework in reinforcement learning (RL) for representing actions at different temporal scales and levels of abstraction. The option framework has shaped subsequent work in the area, and still defines the terms in which the problem of representation learning of hierarchical actions and knowledge is formulated and addressed in RL.
2019 Prominent AIJ Paper Award
The dropout learning algorithm
P Baldi, P Sadowski - Artificial intelligence, 2014 - Elsevier
URL: https://www.sciencedirect.com/science/article/pii/S0004370214000216
Dropout has become a key machine learning technique used mainly to avoid overfitting when training large neural networks. The mathematical analysis in the paper uncovers the properties that have made dropout a cornerstone in deep learning. The article also provides connections to other areas of statistics, and to the theory of ensemble learning and spiking neurons.