COG 2022 Football AI Competition
June - August, 2022
COG 2023 Football AI Competition, please refer to Link
Football (a.k.a. soccer) is one of the most popular sports. Teaching AI to play football is quite challenging because the agents need to learn complex concepts such as passing and defensing. Training football agents requires a balance of short-term control and high-level strategies, including how to overcome opponent's defense in order to score goals. The Football Environment, a reinforcement learning environment, provides challenging and interesting opportunities to train AI playing football in an advanced, physical-based 3D simulator. This environment implements a complete football game and includes the most common football concepts, for example goals, fouls, corners, penalty kicks, yellow cards, red cards and offsides.
In COG 2022 competition, we provide two tracks for the football challenge. One track is under the scenario 5vs5, where both left and right team control 4 players in each team except the goal keeper of the corresponding team. Another track is under the 11vs11 scenario, where both sides control the full set of players (11 players) in each team.
Jidi platform has integrated the Football Environment into its environment set. The algorithms for this competition are going to be submitted through the platform. Jidi is an online algorithmic countermeasure platform, which provides enormous games and superior competitions. The platform also provides real time rankings. Once participants submit their algorithms, rankings of the corresponding games will be shown on the leaderboard. Currently, the platform has thousands of users, nearly hundreds of games and tens of competitions.
Playing football with AI is interesting and challenging. Join us and submit your algorithms!
i.5vs5 Track: http://www.jidiai.cn/compete_detail?compete=15
ii.11vs11 Track:http://www.jidiai.cn/compete_detail?compete=16
Haifeng Zhang is an associate professor at Institute of Automation, Chinese Academy of Sciences (CASIA), leading the Collective Decision Intelligence Lab. His research areas include reinforcement learning, game AI, game theory and computational advertising.