Search Unity

  1. Unity 6 Preview is now available. To find out what's new, have a look at our Unity 6 Preview blog post.
    Dismiss Notice
  2. Unity is excited to announce that we will be collaborating with TheXPlace for a summer game jam from June 13 - June 19. Learn more.
    Dismiss Notice
  3. Dismiss Notice

Question Unity MLAgents Help on Reward Functions and Speeding Up the Training

Discussion in 'ML-Agents' started by orhun868, Mar 3, 2024.

  1. orhun868

    orhun868

    Joined:
    Feb 22, 2024
    Posts:
    5
    Hello! I am designing and trying to train a dynamic table on Unity. I have created the code but I am not sure If the training works since it is too slow. I tried to increase the number of the environments but they don't work when I do that. I use localPosition everywhere. Still, I could not figure out what should I correct. Also, I am not sure my reward function is efficient enough. If you can examine it I would love to hear some suggestions.
    Here is the repo: github.com/elymsyr/dynamicMachine_mlagents