Why my prompt shows that my model is Not Training

Unity Engine
, , ,
1

Hello,everyone. I’m very new to Reinforcement Learning and Unity:(.
I play the Unity’s Github repositories 3DBall demo and use this command

D:\Code\ml-agents>mlagents-learn config/ppo/3DBall.yaml --run-id=3DBall --inference

then it showed that
mlagents.trainers.exception.UnityTrainerException: Previous data from this run ID was found. Either specify a new run ID, use --resume to resume this run, or use the --force parameter to overwrite existing data

so I changed my commands to
D:\Code\ml-agents>mlagents-learn config/ppo/3DBall.yaml --run-id=3DBall --inference --force
then I pressed the play button in Unity editor

then like this

[INFO] 3DBall. Step: 12000. Time Elapsed: 25.483 s. Mean Reward: 1.229. Std of Reward: 0.813. Not Training.
[INFO] 3DBall. Step: 24000. Time Elapsed: 37.375 s. Mean Reward: 1.269. Std of Reward: 0.761. Not Training.
[INFO] 3DBall. Step: 36000. Time Elapsed: 51.548 s. Mean Reward: 1.168. Std of Reward: 0.696. Not Training.
[INFO] 3DBall. Step: 48000. Time Elapsed: 64.671 s. Mean Reward: 1.245. Std of Reward: 0.771. Not Training.
[INFO] 3DBall. Step: 60000. Time Elapsed: 78.200 s. Mean Reward: 1.246. Std of Reward: 0.724. Not Training.

What should I do to solve this problem? Please help me:((sorry about my poor English,==)

2

Running the CLI with --inference puts ml-agents in inference mode, where it won’t train. Remove that flag and it should train.