Live data from Hacker News

Viewing profile — alexleegk

alexleegk

HN member
Joined
Thu, May 11, 2017, 8:02 PM UTC
HN karma
13
Public activity
6 items

About alexleegk

No profile information was provided.

Recent public activity

  1. comment
    Comment #15723738

    Both AirSim and CARLA aim to fill in similar gaps in the current state of photorealistic simulators for perception and control research. Here are some differences one of my collegu…

  2. comment
    Comment #14783776

    It would be great if the summary had all the 5 words, so that I can review their definitions at the end. Some of my correct answers could have been educated guesses, but I'd still …

  3. comment
    Comment #14320543

    You could also use deep features (pre-trained for ImageNet classification) and use them in your Q-function approximator in such a way that the Q-function is linear wrt some high-le…

  4. comment
    Comment #14320509

    Yes, but what I was trying to get to is that even if the drone can handle the payload, the drone becomes too heavy to crash safely, and it might break more easily (after falling do…

  5. comment
    Comment #14319176

    It's also probably because it's a lot easier to use an off-the-shelf commercial drone than to build/modify one (from a researcher's perspective), and commercial drones typically al…

  6. comment
    Comment #14319072

    That's what Sadeghi and Levine [1] do in their work. They train in simulation in a lot of randomly generated scenes. Since the drone is trained with such a diverse set of scenes, t…