![quake 3 bots quake 3 bots](https://thumbor.forbes.com/thumbor/640x390/http://b-i.forbesimg.com/erikkain/files/2013/07/quake-3-arena.jpg)
The “FTW” agents are DeepMind’s, which played against themselves in a team of 30. A graph showing the Elo (skill) rating of various players. So: clearly the AI agents are the better players. This compared to 43 precent probability for average human players, and 52 percent probability for strong human players. The bot-only teams were most successful, with a 74 percent win probability. To test the AI agents’ abilities, DeepMind held a tournament, with two-player teams of only bots, only humans, and a mixture of bots and humans squaring off against one another. However, this does not necessarily mean that DeepMind’s bots faced a greater challenge Dota 2 is overall a much more complex game than the stripped-down version of Quake III that was used in this research. Instead, they learned to play just by looking at the visual input from the screen, the same as a human. Unlike OpenAI’s Dota 2 bots, DeepMind’s agents also didn’t have access to raw numerical data about the game - feeds of numbers that represents information like the distance between opponents and health bars. This ensured the bots weren’t learning strategies that only worked on a single map. To make the challenge harder for the agents, each game was played on a completely new, procedurally generated map.