This is What Happens When You Teach an AI to Play Hide and Seek

The team at OpenAI observed agents discovering progressively more complex tool use while playing a simple game of hide-and-seek.

Through training in their new simulated hide-and-seek environment, agents build a series of six distinct strategies and counterstrategies, some of which we did not know our environment supported.

The self-supervised emergent complexity in this simple environment further suggests that multi-agent co-adaptation may one day produce extremely complex and intelligent behavior.

You can find a detailed analysis and breakdown of this experiment at OpenAI

(Photo: onenewspage.com) "The Craft: Legacy" coming soon The 1996 cult classic "The Craft" will be getting a...
(Photo: Williams Sonoma) Celebrating the holidays with Dolly Parton The queen of country Dolly Parton is...
(PHOTO: PAT GREENHOUSE/GLOBE STAFF) Nusr-Et Boston restaurant forced to close days after the grand opening...
(Photo: Anwar Hussein/Getty Images) Enjoy your tea like Her Majesty The Queen of England is known for her...
(Photo: Getty Images) Easy DIY Whipped Hot Chocolate Hot chocolate is a traditional hot drink for colder...
(Photo: Netflix) The new story of the Holmes family The original Sherlock Holmes series might have focused...
(Photo: Madame X Tour) Madonna is working on her own biopic Pop music icon Madonna will be working with...
> (PHOTO: SAMIR HUSSEIN/GETTY IMAGES) Prince Harry celebrates his birthday with CAMFED Prince Harry is...
(Photo: Hello Kitty Levis) Sanrio celebrates big anniversary with Levi's The creator of the iconic Hello...
(Photo: Reuters) Kim is stepping away from reality TV to save her relationship Before becoming Mrs. Kanye...
(Photo: dnaindia.com) J.K Rowling backlash over new book release A new book is due to hit shelves, but it is...
(Photo: Colleen Hayes/NBCU Photo Bank/NBCUniversal via Getty Images via Getty Images) "Parks and Recreation" cast...