Search Unity

  1. Megacity Metro Demo now available. Download now.
    Dismiss Notice
  2. Unity support for visionOS is now available. Learn more in our blog post.
    Dismiss Notice

Resolved Q-Learning implementation

Discussion in 'ML-Agents' started by mateolopezareal, Jun 18, 2020.

  1. mateolopezareal

    mateolopezareal

    Joined:
    Jun 4, 2020
    Posts:
    54
    Is there a way to implement a Q-Learning algorithm in Ml-agents?
     
  2. ervteng_unity

    ervteng_unity

    Unity Technologies

    Joined:
    Dec 6, 2018
    Posts:
    150
    mateolopezareal likes this.
  3. celion_unity

    celion_unity

    Joined:
    Jun 12, 2019
    Posts:
    289
    mateolopezareal likes this.
  4. lgendrot

    lgendrot

    Joined:
    Jul 23, 2017
    Posts:
    4
    @celion_unity @ervteng_unity

    Massive necro but...ARE there any plans to document an interface for custom trainers? Unless I'm missing something crucial there's nothing stopping us from mimicking the structure of the current implementations, but an official way would obviously be preferable.
     
  5. celion_unity

    celion_unity

    Joined:
    Jun 12, 2019
    Posts:
    289
    @lgendrot Custom trainers are something that we'd like to do in the future, but still no definite timelines. We took the first steps towards a plugin system here - we would take a similar approach for registration of custom trainers, but I think we'd need to do more working making our training code more modular and reusable.
     
    lgendrot likes this.
  6. lgendrot

    lgendrot

    Joined:
    Jul 23, 2017
    Posts:
    4
    Ah cool, thanks for drawing my attention to that PR
     
  7. ademord

    ademord

    Joined:
    Mar 22, 2021
    Posts:
    49
    is it me or the Gym Wrapper examples are deprecated since baselines doesnt work with TF2.0, the docs here should be updated to use stable-baselines3, which is giving me errors and I can't get help atm on my thread. @celion_unity