The winner is an AI bot from Elon Musk backed start-up OpenAI who went on to defeat world’s several best players of the game in one-on-one matches multiple times. However, the shocking upset as when the AI bot defeated champion Danylo ‘Dendi’ Ishutin in multiplayer online battle arena Defense of the Ancients 2 (Dota 2) in two back-to-back demonstration matches. Elon Musk celebrated the bot’s victory in a tweet.
— Elon Musk (@elonmusk) August 12, 2017 OpenAI describes it as “a step towards building AI systems which accomplish well-defined goals in messy, complicated situations involving real humans”. To gear up for the competition, the bot underwent two weeks of training that was in the form of real-time learning, which allowed the bot to collect “lifetimes of experience” in a short span of time. Explaining the significance of what OpenAI had built in a blog post, they said: “Dota 1v1 is a complex game with hidden information. Agents must learn to plan, attack, trick, and deceive their opponents. The correlation between player skill and actions-per-minute is not strong, and in fact, our AI’s actions-per-minute are comparable to that of an average human player.” The software taught itself how to play the game by playing thousands of matches, developing strategies and gaining understanding as it proceeded. “Our bot has learned—entirely via self-play—to predict where other players will move, to improvise in response to unfamiliar situations, and how to influence the other player’s allied units to help it succeed.” In a video explaining the project (below), OpenAI co-founder and CTO Greg Brockman said, “Dota’s a great testbed for artificial intelligence; it’s a very complicated game with a large competitive scene. The rules of Dota are so complicated [that] if you just think really hard about how the game works and try to write those rules down, you’re not even going to be able to reach the performance of a reasonable player.”
The International was OpenAI “introducing our Dota product to the world and see if they can reach the world of the top human professionals,” Brockman said. In the future, OpenAI wants to “mix AIs and humans on a single team and reach a level of performance that neither of them can reach on their own,” according to Brockman. “AI can be extremely beneficial to humanity and it’s going to require fundamental advances to see what it’s really capable of.”
