Search Unity

  1. Welcome to the Unity Forums! Please take the time to read our Code of Conduct to familiarize yourself with the forum rules and how to post constructively.

Question vis_encode_type for List<float> and creating channeled observations?

Discussion in 'ML-Agents' started by JustnTrying, Jan 21, 2023.

  1. JustnTrying

    JustnTrying

    Joined:
    Sep 24, 2021
    Posts:
    7
    For doing reinforcement learning on a board game (which has specific connected fields), I'd like to include some kind of convolutions for my network. I saw that you can specify this by selecting an appropiate vis_encode_type in the training config file, but I'm wondering if this is only going to work for visual observations (e.g. Camera/Texture sensors)?

    I find it easier to encode the board state myself and feel like using a camera sensor would be way too much here, perhaps even misleading.

    So the question is: can I still use convolutions for simple observations (List of floats)?

    Additionally, I'd like to encode multiple channels (one for each type of game piece), how can I do this in the CollectObservations?
     
  2. hughperkins

    hughperkins

    Joined:
    Dec 3, 2022
    Posts:
    191
  3. hughperkins

    hughperkins

    Joined:
    Dec 3, 2022
    Posts:
    191
    (Note that I'm pretty sure that mlagents expects images to be at least 20x20)
     
  4. JustnTrying

    JustnTrying

    Joined:
    Sep 24, 2021
    Posts:
    7
    Allright, I'll have a look at that, thank you!
    Can I still specify the vis_encode_type in the config, or do I have to do something specific on the C# side for that?