If one thinks that it’s a good opportunity to attack a human player, the other four of them will think the same and will join in the attack. This gives the appearance of great coordination in teamfights—coordination with a precision and rigor that human teams can’t match. Human players have a mental model of the entire game, an understanding of its rules, and hence can recognize that something is amiss; In its millions of games played against itself, OpenAI appears to have never picked up the technique of pulling, and so it has never learned to play against it. So when a human team starts pulling, the bot doesn’t recognize the situation and doesn’t really know what to do.
This news content is a computer generated summarized version of the original article and the authenticity of the original content has not been verified. Please click on the View Article button to refer to the actual content.