RL Course - Multiple ML Agents Training

Course
1

Hi,

These are the instructions.

" This hands-on will be different since to get correct results you need to train your agents from 4 hours to 8 hours . And given the risk of timeout in Colab, we advise you to train on your computer. You don’t need a supercomputer: a simple laptop is good enough for this exercise."

I think AMD Radeon Pro 5500M, the GPU on my Mac cannot be used for training locally. Is that correct ?
Can Intel Iris(R) GPU with 7.8 GB be used ?
Other options ?
Are there instructions to use AWS GPUs somewhere. I am willing to use it and upload.

Thanks,
Mohan

2

Any help ? Anyone managed to use AWS ? Really need the certificate for the resume.
Wondering more about the cost than the setup. I think it is a Jupyter server on AWS/Sagemaker.
Thanks,
Mohan

3

Hi,
How do I log in to Discord to view the discussions ? I could ask there. Now my Unit 8 PPO notebook is not found even after I authorize github to access it.
Thanks,
Mohan