crowdAI is shutting down - please read our blog post for more information
ViZDoom Reinforcement Learning
By Poznan University of Technology
about 2 years ago
From 33 teams submitted 152 agents, the 3 best submissions from 3 different teams according to leaderboard were selected for final evaluation on 10 new unknown maps.
The two best bots from 2017’s edition and the best bot from 2016’s edition have been added to these matches.
here are the winners of the Visual Doom AI Competition 2018 - Multiplayer Track (2):
1) Ben Bell
2) TSAILAB - Tsinghua University & Tencent AI Lab
3) Michael Krax
You’ll find all the final result scores on the winner page.
Thanks to all the participants who submitted solutions and participated to this challenge as well as for being involved in the crowdAI community! Congratulations to the winners!