ml-agents 训练

GitHub - Unity-Technologies/ml-agents: Unity Machine Learning Agents Toolkit

Train:

在anaconda prompt中(需要pytorch环境)

 cd D:\ml-agents-release_16

 mlagents-learn .\config\ppo\3DBall.yaml --run-id=ball

如果是上次训练中断了,

mlagents-learn config/ppo/3DBall.yaml --run-id=first3DBallRun --resume

或者删除D:\ml-agents-release_16文件夹下的result 文件夹。

Your trained model will be at results/<run-identifier>/<behavior_name>.onnx where <behavior_name> is the name of the Behavior Name of the agents corresponding to the model. This file corresponds to your model's latest checkpoint. You can now embed this trained model into your Agents by following the steps below,

  1. Move your model file into Project/Assets/ML-Agents/Examples/3DBall/TFModels/.
  2. Open the Unity Editor, and select the 3DBall scene as described above.
  3. Select the 3DBall prefab Agent object.
  4. Drag the <behavior_name>.onnx file from the Project window of the Editor to the Model placeholder in the Ball3DAgent inspector window.
  5. Press the Play button at the top of the Editor.
  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值