https://github.com/thepredictivedev/super-mario-playing-agent-using-ppo

An agent trained using the principles of SPTDL using PPO RL algorithm on a CNN.
https://github.com/thepredictivedev/super-mario-playing-agent-using-ppo

Last synced: about 1 month ago
JSON representation

An agent trained using the principles of SPTDL using PPO RL algorithm on a CNN.

• Host: GitHub
• URL: https://github.com/thepredictivedev/super-mario-playing-agent-using-ppo
• Owner: ThePredictiveDev
• Created: 2024-01-26T22:40:33.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-01-26T23:03:07.000Z (11 months ago)
• Last Synced: 2024-01-27T01:31:47.133Z (11 months ago)
• Language: Jupyter Notebook
• Size: 1.87 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Super Mario Playing Agent Using PPO

 An agent trained using the principles of SPTDL using PPO RL algorithm on a CNN. 

## Some of the Models to Test are Given Below

https://drive.google.com/drive/u/3/folders/1UKtPzQZOgffovf6KVbVzF5HACcB58dF1?q=parent:1UKtPzQZOgffovf6KVbVzF5HACcB58dF1

### libraries being used are outdated and hence appropriate versions are given as comments, kindly update libraries accordingly before running the code