Search Unity

Search Results

Search Again
  1. Sephraih
    Post

    Setting external rewards to multiple agents

    Thanks, I have stumbled upon the scriptable objects once, but believe i got stuck at some point and decided to revert to independent classes,...
    Post by: Sephraih, Apr 21, 2020 in forum: ML-Agents
  2. Sephraih
    Post

    Setting external rewards to multiple agents

    Sorry, the rewards were a bit misleading, thanks a bunch though, I believe your answer put me on the right track. It was all about the issue of...
    Post by: Sephraih, Apr 20, 2020 in forum: ML-Agents
  3. Sephraih
    Post

    Setting external rewards to multiple agents

    This is an option too I guess, a horrible one.: if (dmger.GetComponent<PlayerAgent>() != null) {...
    Post by: Sephraih, Apr 19, 2020 in forum: ML-Agents
  4. Sephraih
    Post

    Setting external rewards to multiple agents

    i considered a few approaches - an inheritance structure (wouldnt be sure how to manage it well, though) - a helper object, that is static for...
    Post by: Sephraih, Apr 19, 2020 in forum: ML-Agents
  5. Sephraih
    Thread

    Setting external rewards to multiple agents

    Hello there, So far I have been using " GetComponent<PlayerAgent>().SetReward(x); " to apply environment rewards to my agents, which have been...
    Thread by: Sephraih, Apr 19, 2020, 6 replies, in forum: ML-Agents
  6. Sephraih
    Post

    Displaying custom metrics on tensorboard via ml-agents during / after training.

    Explains a lot, hah - thanks!
    Post by: Sephraih, Apr 17, 2020 in forum: ML-Agents
  7. Sephraih
    Post

    Displaying custom metrics on tensorboard via ml-agents during / after training.

    0.14.0 with python 3.7 (the combination seemed to work so far)
    Post by: Sephraih, Apr 13, 2020 in forum: ML-Agents
  8. Sephraih
    Post

    Training versus a pretrained Brain

    Ah, thanks, seems like i misunderstood the inference option to train if connected to a trainer. - oddly, if i keep one of the self-play agents set...
    Post by: Sephraih, Apr 13, 2020 in forum: ML-Agents
  9. Sephraih
    Thread

    Training versus a pretrained Brain

    Of course, self-play already covers this during the training, however, I would love to be able to reuse a trained brain to pit a variety of new...
    Thread by: Sephraih, Apr 13, 2020, 2 replies, in forum: ML-Agents
  10. Sephraih
    Post

    Displaying custom metrics on tensorboard via ml-agents during / after training.

    Thanks a bunch, that missing import did bring me closer to the issue - when implementing the code earlier, i wasn't able to find any import i was...
    Post by: Sephraih, Apr 13, 2020 in forum: ML-Agents
  11. Sephraih
    Thread

    Displaying custom metrics on tensorboard via ml-agents during / after training.

    Hello there, I stumbled upon this in the mlagents documentation: Custom Metrics from C# To get custom metrics from a C# environment into...
    Thread by: Sephraih, Apr 11, 2020, 7 replies, in forum: ML-Agents
Showing results 1 to 11 of 11
Search Again