Search Unity

Conv3D for Visual Observation?

Discussion in 'ML-Agents' started by leo2r, May 10, 2022.

  1. leo2r

    leo2r

    Joined:
    Mar 14, 2022
    Posts:
    10
    Hi,

    For an environment we are building, we think the best approach is to use a Conv3D as the agent's observation. Is this possible using the ml-agents pipeline? Can one define custom observation spaces? I read through the documentation and couldn't find anything about 3D CNNs.

    Thanks in advance!
     
    leo2r, May 10, 2022
    #1

  2. mbaske

    mbaske

    Joined:
    Dec 31, 2017
    Posts:
    473
    mbaske, May 12, 2022
    #2

  3. leo2r

    leo2r

    Joined:
    Mar 14, 2022
    Posts:
    10
    leo2r, Jun 7, 2022
    #3

  4. mbaske

    mbaske

    Joined:
    Dec 31, 2017
    Posts:
    473
    No, haven't really followed up on this.
     
    mbaske, Jun 13, 2022
    #4