Home / Gaming / OpenAI’s ‘Dota 2’ neural nets are defeating human opponents

OpenAI’s ‘Dota 2’ neural nets are defeating human opponents

Artificially intelligent systems taking on human competitors is a grand tradition of computer science; thankfully, we’re still in the cute stages that don’t feel quite like War Games yet. For its part, OpenAI has been trying its hand at Dota 2 competitive play, and its bots are starting to win against some skilled opponents under certain conditions.

The Elon Musk co-founded venture is aiming to raise awareness for where AI technologies are now and how the tech industry can promote safe advances that benefit everyone in the future. While playing an unabashedly nerdy video game better than human opponents may seem to be a weird place to expend extensive resources, it’s all the continuation of where AlphaGo and Deep Blue have taken us before: building machines that can beat humans in seemingly simple games.

Unlike decidedly more turn-based games like chess or Go, Dota 2 is a title that requires plenty of real-time decision-making. While Google’s AlphaGo sometimes took minutes to decide how to respond to a particularly well-crafted move, OpenAI Five, as it’s called, does not have that luxury, as its opponent would be making moves in the meantime. These games are operating at 30 frames per second for an average of 45 minutes, OpenAI says, resulting in about 80,000 frames, of which the system analyzes one-quarter.

This blog post has plenty of the nitty-gritty technical details if you’re interested.

This is plenty resource-intensive — OpenAI Five is running on 124,000 cores on Google Cloud — and while this isn’t OpenAI’s first public experimentation playing Dota 2, what makes this interesting is that, compared to its previous efforts in 1v1 matches, this is a team of five distinct neural nets working together to best human opponents.