search

starry-sky6688 / MADDPG

Pytorch implementation of the MARL algorithm, MADDPG, which correspondings to the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments".
537 stars 83 forks source link

how to use this project to train a new model? #36

Closed Aib-star closed 1 year ago

Aib-star commented 1 year ago

how to use this project to train a new model?

starry-sky6688 commented 1 year ago

Just delete the .pkl files in model/simpletag/agent{0,1,2}, and then use the following command

$ python main.py --scenario-name=simple_tag --evaluate=False

Aib-star commented 1 year ago

不对，我用了如下命令：python main.py --scenario-name=simple_tag。其实你的初始命令也一直在训练，因为evaluate的值默认为False。

At 2023-10-20 14:36:40, "starry-sky6688" @.***> wrote:

Just delete the .pkl files in model/simpletag/agent{0,1,2}, and then use the following command

$ python main.py --scenario-name=simple_tag --evaluate=False

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>