willwhitney
Joined 15 years ago
Karma
1,119
Submissions
83
Member since
Apr 12
ML researcher.
View on Hacker NewsRecent submissions
Comment · 5 years ago
Would it be bad if we made advertising... illegal? In small part because it would reduce the principal-agent disparity between what you want to do and what Google wants you to do, but more importantly because it would remove the incentive to create blogspam and game the results.
Advertising serves a positive purpose by informing people about products that they will like and otherwise would not find. It also serves a negative purpose by attempting to cause people to make decisions which are not in their best interests.
I am genuinely curious what proportion of ads seen serve each of those two purposes.
Comment · 6 years ago
That dip is more than 4M people, so I think it's still unexplained. Perhaps due to a shift in response rates or another artifact of COVID churn in the survey methodology?
Comment · 8 years ago
You can actually drag and drop multiple notes into a tag, no find and replace necessary. Minor point though.
Comment · 9 years ago
They have a grammatical error ("deliciously looking") in their (2) step.
Comment · 9 years ago
Handling delays (and the uncertainty they entail) is a huge challenge, and I think it'll be a rich area of research. The simplest part of the problem is that delays in action or perception also slow the propagation of reward signals, and credit assignment is still a really hard problem.
Thinking further afield, future models could learn to adapt their expectations to fit the behavior of a particular opponent. This kind of metalearning is pretty much a wide open problem, though a pair of (roughly equivalent) papers in this direction recently came out from DeepMind: https://arxiv.org/abs/1611.05763 and OpenAI: https://arxiv.org/abs/1611.02779 It's going to be really exciting to see how these techniques scale.
Comment · 9 years ago
Yup, it's definitely an advantage to get all the correct values from the game state. But not as much as you might think; the vision portion of a DQN or similar trains quite quickly.
Plus, our bot doesn't have any clue about projectiles. We don't know where they live in memory, so the network doesn't get to know about them at all.
Comment · 10 years ago
Once a startup gets bought, I look for alternatives.
If they don't shut down, I still learned something new! But usually they do.
In this case, I landed on Fantastical [1] — it's a little pricy but completely worth it. (Mac/iOS only.)
Comment · 10 years ago
I independently wrote a version of this for OS X: https://github.com/willwhitney/live-earth-desktop