Congratulations to the #IJCAI2021 best paper award winners

The IJCAI-2021 awards were announced during the opening ceremony of the International Joint Conference on Artificial Intelligence (IJCAI-21). The honours included the 2021 AIJ classic paper award, the AIJ prominent paper award, and the IJCAI-JAIR best paper prize.

AIJ 2021 classic paper award

This award recognizes outstanding papers, exceptional in their significance and impact, that were published at least 15 years ago, in the journal Artificial Intelligence (AIJ).

Planning and acting in partially observable stochastic domains
Leslie Kaelbling, Michael Littman, Anthony Cassandra

This paper brought partially observable Markov decision processes (POMDPs) from the field of operational research to the field of AI. It provides an excellent account of the theory behind POMDPs, which demystified the field for a generation of researchers, and popularised their use in both AI and robotics. This paper has been instrumental in advancing the field of sequential decision making.

Read the paper in full here.

Find out more in this post from Brown University.

AIJ 2021 prominent paper award

This award recognizes outstanding papers, that are exceptional in their significance and impact, published not more than seven years ago in AIJ. This year, the award committee recognised two papers.

Efficient crowdsourcing of unknown experts using bounded multi-armed bandits
Long Tran-Thanh, Sebastian Stein, Alex Rogers, Nicholas Jennings

This paper developed the first comprehensive framework for the rigorous mathematical analysis for task allocation in crowdsourcing systems, along with a new sequential decision-making model, with provable performance guarantees. These contributions have significantly impacted subsequent work by both academic and industry researchers.

Read the paper in full here.

Algorithm runtime prediction: Methods & evaluation
Frank Hutter, Lin Xu, Holger Hoos, Kevin Leyton-Brown

This paper is a reference in the field of algorithm runtime prediction. It provides a unifying, technical overview, novel technical contributions, extensions of existing methodology, and comprehensive empirical analysis over domains such as the travelling salesperson, propositional satisfiability and mixed integer programming problems.

Read the paper in full here.

2021 IJCAI-JAIR best paper prize

This prize is awarded to an outstanding paper published in the last five years in the Journal of Artificial Intelligence Research (JAIR). The winner is selected based on significance of the paper and the quality of presentation.

Learning explanatory rules from noisy data
Richard Evans and Edward Grefenstette

This paper demonstrates one of the first end-to-end differentiable approaches to inductive logic programming. The authors show that it is possible to bridge symbolic and deep-learning approaches, in a way that the logic programming techniques become more robust, and the neural systems become more interpretable.

Read the paper in full here.

We previously reported on the winners of the IJCAI-21 award for research excellence, computers and thought award, and the John McCarthy award. Find out more here.

Lucy Smith , Managing Editor for AIhub.

Lucy Smith , Managing Editor for AIhub.