Design your own RL agent

The malware-score-env and malware-env are available gym environments that you can use to train your own RL agent.

import gym
import gym_malware

env = gym.make("malware-v0")
env = gym.make("malware-score-v0")
env.seed(args.seed)

The environments are inspired by the endgameinc environments available here.

PEsidious has a modified environment that makes use of GAN. The mutations were also added/changed/removed to improve the evasiveness of the malware and maintain functionality by making use of c++.