Search Unity

  1. Welcome to the Unity Forums! Please take the time to read our Code of Conduct to familiarize yourself with the forum rules and how to post constructively.
  2. We have updated the language to the Editor Terms based on feedback from our employees and community. Learn more.
    Dismiss Notice
New Forum User Notice Update to the Unity Editor Software Terms

Food Collector Example Environment

Discussion in 'ML-Agents' started by ek578, Aug 27, 2020.

  1. ek578

    ek578

    Joined:
    Jun 25, 2020
    Posts:
    5
    In the food collector environment, multiple agents are interacting at once. During training, are all agents running the same policy? So basically, it is self-play without randomly substituting older policies?
     
    ek578, Aug 27, 2020
    #1

  2. Hsgngr

    Hsgngr

    Joined:
    Dec 28, 2015
    Posts:
    61
    They are using same brain which means same policy as you said. But I dont think this count as self-play. They basically learn concurrently in a Multiagent RL environment.
     
    Hsgngr, Aug 27, 2020
    #2