The paper also revisits the ViZDoom environment, which is a flexible, easy to use, and efficient 3D platform for research for vision-based reinforcement learning, based on a well-recognized first-person perspective game Doom. The results of the competition lead to the conclusion that, although reinforcement learning can produce capable Doom bots, they still are not yet able to successfully compete against humans in this game. Best-performing agents are described in more detail. The paper discusses the rules, solutions, results, and statistics that give insight into the agents' behaviors.
These aspects, together with the competitive multi-agent aspect of the game, make the competition a unique platform for evaluating the state of the art reinforcement learning algorithms. To play well, the bots needed to understand their surroundings, navigate, explore, and handle the opponents at the same time. The bots had to make their decisions based solely on visual information, i.e., a raw screen buffer. The challenge was to create bots that compete in a multi-player deathmatch in a first-person shooter (FPS) game, Doom.
This paper presents the first two editions of Visual Doom AI Competition, held in 20.
