Stories
Slash Boxes
Comments

SoylentNews is people

Submission Preview

Link to Story

OpenAI bot bursts into the ring, humiliates top Dota 2 pro gamer in 'scary' one-on-one bout

Accepted submission by exec at 2017-08-15 03:03:09
News

Story automatically generated by StoryBot Version 0.2.2 rel Testing.
Storybot ('Arthur T Knackerbracket') has been converted to Python3

Note: This is the complete story and will need further editing. It may also be covered
by Copyright and thus should be acknowledged and quoted rather than printed in its entirety.

FeedSource: [TheRegister]

Time: 2017-08-12 02:00:42 UTC

Original URL: https://www.theregister.co.uk/2017/08/12/openai_bot_beats_top_dota_2_players_in_surprise_match/ [theregister.co.uk] using UTF-8 encoding.

Title: OpenAI bot bursts into the ring, humiliates top Dota 2 pro gamer in 'scary' one-on-one bout

--- --- --- --- --- --- --- Entire Story Below --- --- --- --- --- --- ---

OpenAI bot bursts into the ring, humiliates top Dota 2 pro gamer in 'scary' one-on-one bout

Arthur T Knackerbracket has found the following story [theregister.co.uk]:

In the past hour or so, an AI bot crushed a noted professional video games player at Dota 2 in a series of one-on-one showdowns.

The computer player was built, trained and optimized by OpenAI, Elon Musk’s AI boffinry squad based in San Francisco, California. In a shock move on Friday evening, the software agent squared up to top Dota 2 pro gamer Dendi [teamliquid.net], a Ukrainian 27-year-old, at the Dota 2 world championships dubbed The International [dota2.com].

The OpenAI agent beat Dendi in less than 10 minutes in the first round, and trounced him again in a second round, securing victory in a best-of-three match. "This guy is scary," a shocked Dendi told the huge crowd watching the battle at the event. Musk was jubilant.

OpenAI first ever to defeat world's best players in competitive eSports. Vastly more complex than traditional board games like chess & Go.

— Elon Musk (@elonmusk)

According to OpenAI, its machine-learning bot was also able to pwn two other top human players this week: SumaiL [teamliquid.net] and Arteezy [teamliquid.net]. Although it's an impressive breakthrough, it’s important to note this popular strategy game is usually played as a five-versus-five team game – a rather difficult environment for bots to handle.

Complex strategy games are all the rage in the AI world at the moment. Some of the biggest companies, such as Facebook and Google's DeepMind, are racing [theregister.co.uk] to conquer games including StarCraft or Montezuma’s Revenge.

Dota 2 is similar to StarCraft in some respects, as it requires careful planning. Players need to gauge when to attack and trick opponents to defeat enemy units. It’s also an imperfect information game unlike chess or Go, where both players have access to the same information and are on equal footing.

    Youtube Video [youtube.com]

It’s unclear exactly how OpenAI’s bot was trained as the research outfit has not yet published any technical details. But a short blog post [openai.com] today describes a technique called “self-play” in which the agent started from scratch with no knowledge and was trained using supervised learning over a two-week period, repeatedly playing against itself. Its performance gets better over time as it continues to play the strategy game. It learns to predict its opponent's movements and pick which strategies are best in unfamiliar scenarios.

OpenAI said the next step is to create a team of Dota 2 bots that can compete or collaborate with human players in five-on-five matches. ®

    PS: Elon Musk tweeted [twitter.com] this evening to say AI is, right now, a bigger threat to the world than North Korea, adding: "Nobody likes being regulated, but everything – cars, planes, food, drugs, etc – that's a danger to the public is regulated. AI should be too."


                                        Sponsored:
                                        The Joy and Pain of Buying IT - Have Your Say [theregister.com]
                               

-- submitted from IRC


Original Submission