Search Unity

Search Results

Search Again
Page 1 of 3
  1. MarkTension
    Post

    Official Post Your ML-Agents Project

    This project is actually from a while back, but thought of it recently recently because it's currently on display in Taipei. We used ml-agents to...
    Post by: MarkTension, Feb 7, 2024 in forum: ML-Agents
  2. MarkTension
    Post

    Custom nn with MLAgents

    One thing you can try is configuring the actual ml-agents code, and basically add the convolutions you want. I did this once by adding an extra...
    Post by: MarkTension, Oct 11, 2021 in forum: ML-Agents
  3. MarkTension
    Thread

    Anyone successfully used ml-agents visual observations with first-person gameplay?

    Hi all, I was wondering if anyone could share some success stories, or not-a-success-stories, using visual observations in a first person agent...
    Thread by: MarkTension, Oct 11, 2021, 2 replies, in forum: ML-Agents
  4. MarkTension
    Thread

    Expected reward in which c# script ?

    Hi! I'm trying to get access to expected reward from my agent class. In previous versions I could find it in the Academy.cs , but I can't seem to...
    Thread by: MarkTension, Nov 24, 2020, 0 replies, in forum: ML-Agents
  5. MarkTension
    Post

    How to get expected reward or action probabilities during inference mode?

    I'd be interested in just visualising in e.g. the UI how the expected reward changes depending on where the agent is in the environment, and also...
    Post by: MarkTension, Oct 13, 2020 in forum: ML-Agents
  6. MarkTension
    Thread

    How to get expected reward or action probabilities during inference mode?

    Hi! I'd like to get expected reward or action probabilities during inference mode. Is there a place in the code (e.g. a barracuda script) where I...
    Thread by: MarkTension, Oct 12, 2020, 3 replies, in forum: ML-Agents
  7. MarkTension
    Post

    Can I change the number of channels for a visual observation?

    For anyone who cares, using the new sensor also increased my training speed x2. Also having multiple sensors was implementable using child...
    Post by: MarkTension, Sep 18, 2020 in forum: ML-Agents
  8. MarkTension
    Post

    Can I change the number of channels for a visual observation?

    I don't get this. Do you mean this automatically happens when I add the sensorComponent script to the agent gameobject? Or do I manually have to...
    Post by: MarkTension, Sep 3, 2020 in forum: ML-Agents
  9. MarkTension
    Post

    Can I change the number of channels for a visual observation?

    Thanks for sharing this! I'm trying to use it but I've got a few questions: To get it to work I've imported the scripts into my project. Then...
    Post by: MarkTension, Sep 2, 2020 in forum: ML-Agents
  10. MarkTension
    Post

    Can I change the number of channels for a visual observation?

    Sounds great! I went ahead and found this unofficial docs release for Grid Sensor (Couldn't find Grid-Sensor in master branch's docs/ folder) My...
    Post by: MarkTension, Aug 31, 2020 in forum: ML-Agents
  11. MarkTension
    Post

    Can I change the number of channels for a visual observation?

    Cool! If significantly faster I'd be interested to try
    Post by: MarkTension, Aug 27, 2020 in forum: ML-Agents
  12. MarkTension
    Post

    Question training stops with RuntimeError: dictionary changed size during iteration

    Great! Happy it got solved
    Post by: MarkTension, Jul 9, 2020 in forum: ML-Agents
  13. MarkTension
    Thread

    Question training stops with RuntimeError: dictionary changed size during iteration

    Hi, Sometimes my training stops with this "dictionary changed size during iteration" error. Is anyone familiar with that? I'm using concurrent...
    Thread by: MarkTension, Jul 6, 2020, 7 replies, in forum: ML-Agents
  14. MarkTension
    Post

    Can I change the number of channels for a visual observation?

    Btw, I can confirm that this is working well now*
    Post by: MarkTension, Jun 29, 2020 in forum: ML-Agents
  15. MarkTension
    Thread

    Can train, but failed to load libcoreclr, libsystem, libdl.

    My custom environment runs and can train, however it crashes every so often due to a time-out error in my command prompt: File...
    Thread by: MarkTension, Jun 23, 2020, 1 replies, in forum: ML-Agents
  16. MarkTension
    Post

    Can I change the number of channels for a visual observation?

    Thank you, this is very clear now! Hope it improves my agent. I guess it should. Until now I was doing a sort of a clunky bit-encoding of 6...
    Post by: MarkTension, Jun 19, 2020 in forum: ML-Agents
  17. MarkTension
    Post

    Can I change the number of channels for a visual observation?

    Hi @celion_unity thanks so far for the help. I didn't get to it last months, but still very interested to try. Finding it difficult to get a...
    Post by: MarkTension, Jun 18, 2020 in forum: ML-Agents
  18. MarkTension
    Post

    LSTM usage logic

    As I understand it, sequence_length means indeed that 64 observations are used during training to learn the temporal relationships. I haven't...
    Post by: MarkTension, Jun 4, 2020 in forum: ML-Agents
  19. MarkTension
    Post

    Why should batch size be >= recurrence's sequence length? Why not horizon?

    Aah I thought a batch includes multiple horizons: (each batch sample being one sequence of length horizon). But from this I get that a batch...
    Post by: MarkTension, May 2, 2020 in forum: ML-Agents
  20. MarkTension
    Thread

    Why should batch size be >= recurrence's sequence length? Why not horizon?

    Hi! as of version 0.15.1, when using recurrence and I set batch size smaller than sequence length I get an error:...
    Thread by: MarkTension, May 1, 2020, 3 replies, in forum: ML-Agents
Showing results 1 to 20 of 43 Next >
Search Again
Page 1 of 3