Tweetovi

Blokirali ste korisnika/cu @jachiam0

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @jachiam0

  1. Prikvačeni tweet
    8. stu 2018.

    Excited to share what I've been working on these last few months! Spinning Up in Deep RL, an educational resource that we hope can bring down the barrier to entry in RL.

    Poništi
  2. proslijedio/la je Tweet
    3. velj

    Compliment people behind their backs.

    Poništi
  3. 3. velj

    Excellent resource for tracking what can go wrong.

    Poništi
  4. proslijedio/la je Tweet
    2. velj

    Performance artist generates virtual traffic jams in Google Maps by pulling a wagon full of smartphones

    Poništi
  5. 1. velj

    A billion years from now, it seems likely that there will be no beings inhabiting the universe that we recognize as human. But what from today's humanity should get preserved? What from this moment in history should future generations always treasure?

    Poništi
  6. proslijedio/la je Tweet
    30. sij

    OpenAI "Spinning Up in RL" now available in PyTorch 🔥

    Poništi
  7. 30. sij

    Check it out: Spinning Up is now a sort of "Rosetta Stone" for deep RL, with simple implementations of VPG, PPO, DDPG, TD3, and SAC in both PyTorch and TFv1.

    Poništi
  8. 30. sij

    Super excited to be using PyTorch as my main deep learning framework now. It's honestly just a pleasure to work with.

    Poništi
  9. 29. sij
    Poništi
  10. 29. sij

    This is so exciting to see! Building production-grade ML+robotics is an incredible accomplishment by the Covariant team.

    Poništi
  11. proslijedio/la je Tweet
    29. sij

    "The task in front of us is not to identify the true or correct moral theory and then implement it in machines. Rather, it is to discover a way of selecting appropriate values that is compatible with the fact that we live in a diverse world.”

    Prikaži ovu nit
    Poništi
  12. 29. sij

    Following up on this: it looks like "set_num_threads" has a side-effect related to preventing MKL from dynamically creating and destroying threads, and fixes the number of MKL threads used. Go figure!

    Prikaži ovu nit
    Poništi
  13. 28. sij

    that feeling when "torch.set_num_threads(torch.get_num_threads())" inexplicably makes your code twice as fast

    Prikaži ovu nit
    Poništi
  14. 25. sij

    If the previous question is looking for something like a least upper bound on this problem, here's a related lower bound question: what are the minimal sufficient conditions for an exercise of power to be legitimate? (Regardless of whether you expect it to always be right.)

    Prikaži ovu nit
    Poništi
  15. 25. sij

    Are there any mechanisms for aggregating what humans believe, and making decisions that impact lots of humans, that you would trust on a deep level to make morally good decisions? (If your idea doesn't fit in a Tweet, and honestly maybe it shouldn't, PM me.)

    Prikaži ovu nit
    Poništi
  16. 24. sij

    that feeling when you finally knock out that one task that's been on the backburner for two weeks because it was too important to phone in but other things were even more urgent

    Poništi
  17. 24. sij

    Every now and then, I think of this and smile. What a spectacular moment in human history.

    Poništi
  18. 22. sij

    I love it when people try to help each other. Even when it doesn't always work out, or when the effort is a bit misguided. Compassion doesn't have to be perfect to be good.

    Poništi
  19. proslijedio/la je Tweet
    20. sij

    Submit your datasets, papers, + abstracts to the 1st-ever AI for Earth Sciences workshop ! 🌍 We're looking for AI/ML applied to challenges in atmospheric physics, oceanography, geology, planetary sciences, space weather, + geo-health:

    Poništi
  20. 20. sij

    2020 goal: not have to preface any email with "sorry for the delay"

    Poništi
  21. 13. sij

    Should training epochs count from 0 or 1?

    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:

    ·