Search Unity

  1. If you have experience with import & exporting custom (.unitypackage) packages, please help complete a survey (open until May 15, 2024).
    Dismiss Notice
  2. Unity 6 Preview is now available. To find out what's new, have a look at our Unity 6 Preview blog post.
    Dismiss Notice
Feedback request: Understanding import & export package workflows Unity 6 Preview now available

Resolved PPO and Q-Learning

Discussion in 'ML-Agents' started by mateolopezareal, Jun 15, 2020.

  1. mateolopezareal

    mateolopezareal

    Joined:
    Jun 4, 2020
    Posts:
    54
    I have reeding about these two algorithms, and I did understand that PPO works with continous actions and continous observations. So if my agent uses discrete values is not using PPO? Is there a way to use Q-Learning in Ml-agents?
     
    mateolopezareal, Jun 15, 2020
    #1

  2. vincentgao88

    vincentgao88

    Unity Technologies

    Joined:
    Feb 7, 2018
    Posts:
    21
    PPO also works with discrete action space and discrete observation space. Currently Q-learning is not implemented in ML-agents
     
    vincentgao88, Jun 15, 2020
    #2
    mateolopezareal likes this.