Live data from Hacker News

Viewing profile — pjrule

pjrule

HN member
Joined
Sat, Nov 25, 2017, 3:32 AM UTC
HN karma
168
Public activity
27 items

About pjrule

[ my public key: https://keybase.io/pjrule; my proof: https://keybase.io/pjrule/sigs/dRL8UZjd-eUL9lwnPnAvmo-bMDkJl_BsBesbrlcMBiQ ]

Recent public activity

  1. story
  2. story
  3. story
  4. comment
    Comment #29700421

    I’ve done something like this in the past with a spreadsheet, but I recently fell out of the habit because of the overhead of taking a few minutes at the end of a long day and open…

  5. story
  6. story
  7. story
  8. story
  9. story
  10. comment
  11. story
  12. comment
    Comment #17679224

    Yeah, Hanson phrases this idea poorly. It might be better to say that creating large backroom software has something of a high barrier to entry. For instance, popular packages like…

  13. story
  14. comment
    Comment #17587796

    Ben Recht also has an excellent series of blog posts (very related to this survey on arXiv, but broader) on the intersection between reinforcement learning and optimal control. An …

  15. story
  16. story
  17. story
  18. story
  19. comment
    Comment #17283668

    That’s excellent! Thanks!

  20. comment
    Comment #17275892

    Thanks so much! I read this (and a few related papers) today. Besides the novel algorithm discussed in the new Atari paper, do you have a reference implementation of online vector …

  21. comment
    Comment #17252277

    As someone working on a reinforcement learning/neuroevolution problem right now, I find this to be extremely exciting. Fewer parameters, ceteris paribus , is always better—the fact…

  22. story
  23. story
  24. comment
    Comment #17088847

    Indeed, I had a similar experience. Perception is strange.

  25. comment
    Comment #16762126

    This is a fantastic idea, and I think I’ll definitely be applying! Have you considered offering two tiers of grants? Most AI side projects don’t necessarily require ~$30k in resour…