search

StepNeverStop / RLs

Reinforcement Learning Algorithms Based on PyTorch
https://stepneverstop.github.io
Apache License 2.0
449 stars 93 forks source link

Hello. I want to know how to use RLs into unity3d-mlagent. #23

Closed strikeman1 closed 3 years ago

strikeman1 commented 3 years ago

I have read your project,but i do not know how to use in mlagent.please teach me,thanks.

StepNeverStop commented 3 years ago
  1. follow the docs in official released ml-agents to build your custom training environment.
  2. type python run.py -u to invoke the default PPO algorithm to interact with Unity Editor
  3. press Start button in Unity Editor to establish a connection for your algorithm and environment.
strikeman1 commented 3 years ago

ok,i will have a try,thank you

strikeman1 commented 3 years ago

do you have wechat ,can i got it,it will communicate with you more convenient

StepNeverStop commented 3 years ago

sorry, you could contact me by e-mail: keavnn.wjs@gmail.com if you need more help.

strikeman1 commented 3 years ago

ok，thank you

strikeman1 commented 3 years ago

问题 why my training has this problem,I use this command-"python run.py -u -a ppo -n run_with_unity" and start unity.

StepNeverStop commented 3 years ago

@strikeman1 Sorry, I totally have no idea about your problem encountered, there is no package named "naming" that is used in this repo. Maybe you could try pip install -e .[unity] and then start your training, or you could try the code in branch dev.

BTW, if you have any questions, plz reopen this issue or create a new one so as I could get it timely.

strikeman1 commented 3 years ago

sry,I know,thx,I have a try

strikeman1 commented 3 years ago

and I want to ask you other question,this project use GPU? I have GPU installed,but it remain have this question new question