OpenAI Five Benchmark

The OpenAI Five Benchmark match is now over!

OpenAI

The OpenAI Five Benchmark match is now over!

Benchmark

Because our training system Rapid⁠ is very general, we were able to teach OpenAI Five many complex skills since June simply by integrating new features and randomizations. Many people pointed out that wards and Roshan were particularly important to include—and now we’ve done so. We’ve also increased the hero pool to 18 heroes. Many commenters thought these improvements would take⁠(opens in a new window) another⁠(opens in a new window) year⁠(opens in a new window). We’ll see how well these new game mechanics work on August 5th!

An aerial view of Rosh4 Healthbars

The latest version of OpenAI Five taking Roshan.

We will play with the following restrictions (the crossed out restrictions are those lifted since the original OpenAI Five blog post), which correspond to the last bits of the game we haven’t integrated:

We’ve increased the reaction time of OpenAI Five from 80ms to 200ms. This reaction time is much closer to human level, though we haven’t seen evidence of changes in gameplay as OpenAI Five’s strength comes more from teamwork and coordination than reflexes.

The final date for the match is August 5, and will run as follows:

  • 12pm PT: doors open
  • 12:30pm PT: livestream begins with “for fun” audience games
  • 1:15pm PT: main event begins: intro and best-of-three versus 99.95th percentile Dota players

If you’d like to attend the match in person in San Francisco, please request an invite⁠(opens in a new window) by Friday July 20 at 11:59p PT; invites will be sent by the end of Monday July 23. Our venue is limited to 300 attendees, so we’ll be selecting invitees based on their answers to the request form. If you’ve already requested an invite, you’ll receive an email linking to this form as well.