Skip to content

PenGym v0.1

Latest
Compare
Choose a tag to compare
@rzvnbr rzvnbr released this 04 Aug 07:05
· 16 commits to main since this release

First public release of PenGym, a pentesting training framework for Reinforcement Learning (RL) agents developed by Japan Advanced Institute of Science and Technology and KDDI Research, Inc. The main characteristic of the framework is that it converts the actions generated by the RL agents into real actions that are executed in a cyber range, thus making it possible to train the pentesting agents in realistic networks.