1. Setup GPU Server - Pommerman/pytorch-pommerman-rl GitHub Wiki

Signup GCP account(DON'T USE USC ACCOUNT)

https://console.cloud.google.com

Retrieval you GCP credits (Email title: 20193_csci_599_30384: Special Topics: Google Cloud Credits for CSCI 599)

1. Click the "Student Coupon Retrieval Link" to verify your student account
2. Redeem your student coupon by opening the link in email "Your Google Cloud Platform Education Grant Coupon"

Create a GPU instance

1. Follow this article(https://cloud.google.com/deep-learning-vm/docs/cloud-marketplace) to create your deep learning instance, but you will have an error. (GPU quotas)
2. Click warning and follow the steps to create a ticket to GCP team or you can't create a GPU server
3. After your GPU quota changed, then repeat step 1 to configure your deep learning frameworks(tensorflow/pytorch), CPU cores, RAM and GPU type
4. Edit your instance and add your ssh public key to the server, then you could log in this server by ssh.