Noam Brown

@polynoamial

Research Scientist at research (FAIR) focused on multi-agent artificial intelligence. Creator of and poker AIs

Pittsburgh, PA
Vrijeme pridruživanja: siječanj 2017.

Tweetovi

Blokirali ste korisnika/cu @polynoamial

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @polynoamial

  1. Prikvačeni tweet
    21. pro 2019.

    I'm honored to see that our multiplayer poker AI was named a runner-up by for Scientific Breakthrough of the Year!

    Poništi
  2. 29. sij

    The key is to reduce the "common knowledge" in the game. This is a really difficult but important problem for AI and one that not many people are working on

    Prikaži ovu nit
    Poništi
  3. 29. sij

    You could make a bot-proof poker variant by having a lot of private actions, like discards. Even better is if those private actions reveal info. E.g., being able to look at a card an opponent discarded (without them knowing). Nobody knows how to make a good AI for games like this

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet
    28. sij
    Poništi
  5. 26. sij

    I know a foreign-born AI professor who can't travel outside the US because she might not be allowed back in. A co-worker of mine made a trip to Canada and was denied re-entry for a year. If we keep turning away talented people, the US will lose its status as a leader in research

    Poništi
  6. 3. sij

    "I would like to specialize in AI, particularly Machine Learning, but from what I've read it seems AI is somewhat of a dead field" <-- From an email I sent to a professor 10 years ago asking for advice on applying to grad school. It's amazing how much AI has changed in a decade

    Poništi
  7. proslijedio/la je Tweet
    13. pro 2019.

    We're releasing "Dota 2 with Large Scale Deep Reinforcement Learning", a scientific paper analyzing our findings from our 3-year Dota project: One highlight — we trained a new agent, Rerun, which has a 98% win rate vs the version that beat .

    Poništi
  8. 12. pro 2019.

    We'll be demoing our Hanabi AI at the Emergent Communication Workshop on Saturday and giving a talk on it at 2:45! I'm also at NeurIPS for the whole week. If you are interested in multi-agent RL, I'm happy to talk!

    Poništi
  9. 9. pro 2019.

    Want to play poker against ? We'll be demoing the AI all day tomorrow (Tuesday) at the booth at !

    Poništi
  10. proslijedio/la je Tweet
    5. pro 2019.

    AI Dungeon 2 is done! 🐲 This has been the product of hundreds of hours, but it's been completely worth it. AI Dungeon 2 is a first of it's kind completely AI generated text adventure that allows you to enter any action you can imagine. Play it here:

    Poništi
  11. 6. pro 2019.

    We have also open sourced all the code!

    Prikaži ovu nit
    Poništi
  12. 6. pro 2019.

    6 months ago we showed with that search was the key to beating top humans in poker. Today , Hengyuan Hu, , and I are announcing new results showing that a similar search algorithm can conquer cooperative partially observable games like Hanabi as well!

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    25. stu 2019.

    Applications for the Facebook AI Residency program are open. US (NYC, Seattle, Menlo Park): UK (London): Deadline: 2020-01-31

    Poništi
  14. proslijedio/la je Tweet

    It is that time of the year where many aspirants will be applying for grad school and tenure track positions. I just wanted to share some advice that I wish I had known when I was going through these things. [continued below]

    Prikaži ovu nit
    Poništi
  15. 20. stu 2019.

    "Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model" -- Really exciting new work from the AlphaZero group at DeepMind!

    Poništi
  16. proslijedio/la je Tweet
    18. stu 2019.

    We are realists if nothing else

    Poništi
  17. 7. stu 2019.

    This has not been universally true (for example, Pluribus)

    Poništi
  18. 30. lis 2019.

    In 2015 our champion poker AI Claudico lost to humans because they found exploitable weaknesses. and fixed this, but it wasn't easy. is impressive, but the real test of any AI system is whether it's robust to adversarial adaptation and exploitation

    Poništi
  19. 24. lis 2019.

    Interested in multi-agent RL, game theory, and/or ML/AI research more broadly? Come intern or work full-time at and do awesome trailblazing research with us! More details: and

    Poništi
  20. 21. lis 2019.

    Applications to the AI Fellowship are due this Friday! If you're unsure what to include in your research statement, check out this great post from 2018 recipient Ruth Fong:

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·