Search Unity

Bug Ml Agents Brain play different while learning

Discussion in 'ML-Agents' started by Moreus, Feb 2, 2021.

  1. Moreus

    Moreus

    Joined:
    Oct 25, 2018
    Posts:
    5
    I Made something similar to Gridword with Grid Sensor.
    My Ml Agent learn really nice but when I try play from lasted brain my ML agent play much worse

    change request form Fixed update script to Decision Requester but don't make difference (only play nice while leaning)



    Version information:
    OS: windows 10
    Unity 2020.1.9f1
    ml-agents: 0.23.0,
    ml-agents-envs: 0.23.0,
    Communicator API: 1.3.0,
    PyTorch: 1.7.0+cu110
     
    Moreus, Feb 2, 2021
    #1

  2. ervteng_unity

    ervteng_unity

    Unity Technologies

    Joined:
    Dec 6, 2018
    Posts:
    150
    Hey warfanel, your video isn't playing.
    Can you try running mlagents-learn with --inference, --time-scale=1, and --resume? If it plays poorly with that, it's most likely that the game behaves differently at high time scales. If not, we'll have to investigate further. Thanks!
     
    ervteng_unity, Feb 2, 2021
    #2

  3. Moreus

    Moreus

    Joined:
    Oct 25, 2018
    Posts:
    5
    I'm sorry video was private.
    Now with "--inference, --time-scale=1, and --resume"

    is still different while learning
    now I have 150+ fps
     
    Moreus, Feb 2, 2021
    #3

  4. Moreus

    Moreus

    Joined:
    Oct 25, 2018
    Posts:
    5
    Moreus, Feb 6, 2021
    #4