Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Battle environment DQN opponent  #16

@jon-d-thomas

Description

@jon-d-thomas

Hi, how exactly did you train the DQN adversary agent for the battle environment? As far as I can see MAgent does not have pre-trained models so I assume you must have trained it using the train_battle.py script. If so, what configuration did you use? Was it a L vs L battle? What was the map size? Were all the parameters default? Is it possible to get the model itself?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions