Skip to content

Differential Learning-Based Testing of Deep RL Agents Playing Super Mario Bros.

License

Notifications You must be signed in to change notification settings

mtappler/dlbt-smb-rl

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

dlbt-smb-rl

This repository contains code implementing an approach for differential learning-based testing of deep RL agents playing Super Mario Bros.

The deep RL code is based on the PyTorch tutorial on training deep RL agent for Super Mario Bros. and we use the gym-super-bros environment.

The approach is described in the paper "Differential Safety Testing of Deep RL Agents Enabled by Automata Learning". More information is going to be added soon.

About

Differential Learning-Based Testing of Deep RL Agents Playing Super Mario Bros.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages