Effective Agents, Dummy Agents and More

A number of Bar-Ilan computer science students won top prizes in the various competitions that are associated with the International Joint Conference on Artificial Intelligence (IJCAI) 2021.

Three of the sixty-four groups that participated in this year's contest were from Bar-Ilan University.

BIU students advanced to the finals of each of the various competitions. The Chef's Hat Reinforcement Learning Competition, for instance, is divided into two tracks: a competitive and a cooperative scenario. In the competitive track, participants use a simulation environment already available to develop the most effective agents to play the Chef’s Hat card game and be the winner. In the cooperative track, they objective is to develop an agent that can increase the chances of a dummy agent winning the game.

Students Ron Binyamini, Liat Schiff and Yair Chanina took first place in the competitive track and second place in the cooperative track.

An additional group, comprised of Or Shabbat, Ofek Yisrael and Sapir Harari, won second place in the competitive track and third place in the cooperative track.

In the Automated Negotiation Competition, Yair Korngut, Daniel Eisenberg, and Ephi Frenkel won first place.

Asaf Tirangle, Inbal Avraham and Joseph Weizman won first place in the Supply Chain Management Competition in the OneShot League, and Sagi Nahum earned third place.

In the Human-Agent Negotiations Competition, Tal Levy, Eyal Cohen, and Lidor Ellis took first place.

Winning teams received cash prizes and have been invited to present an article at a relevant IJCAI workshop.

All of the winning students are from Prof. Kraus's course Advanced Topics in Artificial Intelligence.