Search Unity

  1. All Pro and Enterprise subscribers: find helpful & inspiring creative, tech, and business know-how in the new Unity Success Hub. Sign in to stay up to date.
    Dismiss Notice
  2. Dismiss Notice

WallJump example giving bad results when using PPO only

Discussion in 'ML-Agents' started by Wolf00007, Jun 6, 2021.

  1. Wolf00007

    Wolf00007

    Joined:
    Jan 26, 2019
    Posts:
    14
    Hello!
    So I have been following the article below to learn more about this WallJump example

    https://towardsdatascience.com/an-introduction-to-unity-ml-agents-6238452fcf4c

    and in this article, they used PPO algorithm to train the agent (no curriculum or gail/bc) with slightly adjusted hyperparameters. Their results were very good.

    I have tried to replicate that to see for myself if this will work that well but in my case, the results were pretty bad.
    upload_2021-6-6_13-0-29.png

    Which brings me to my question - how did they achieve such good results using PPO only? The results for SmallJump model were very similar but the BigJump is a difficult task so my results seem to be more real.
    Did I miss something during this training? The article is 1.5 years old so maybe something was changed with this example?

    Thank you in advance for any help/tips with this!
     
  2. andrewcoh_unity

    andrewcoh_unity

    Unity Technologies

    Joined:
    Sep 5, 2019
    Posts:
    157
    Hi @Wolf00007

    I tried to train WallJump locally and it failed for me as well. I'm looking into whether the environment has changed or something more sinister is at play.
     
    Wolf00007 likes this.
  3. Wolf00007

    Wolf00007

    Joined:
    Jan 26, 2019
    Posts:
    14
    Hi @andrewcoh_unity

    Thank you so much for your response! I have noticed two other things:
    1. When I tried to use the models made by Unity, sometimes some of the agents on the scene are acting weird (like they cannot jump during the phase with the big wall). But not all of them, despite all of them having the same models assigned... Not sure what is going on and I don't know how to consistently recreate it.
    2. This is probably something I just don't know myself but when I tried to train the agents on my own, models I created look very different, and they have different extensions.

    This is the Unity one:
    upload_2021-6-8_18-52-50.png

    And this is mine (.onnx instead of .nn):
    upload_2021-6-8_18-53-11.png

    Thanks!
     
  4. Wolf00007

    Wolf00007

    Joined:
    Jan 26, 2019
    Posts:
    14
    Hi there! Do you have any news on this matter? :)
     
unityunity