The Michigan environment is the environment defined as the toy example in Optimal Defense Policies for Partially Observable Spreading Processes on Bayesian Attack Graphs by Miehling, E., Rasouli, M., & Teneketzis, D. (2015). It constitutes a 29-state/observation, 4-action POMDP defense problem.
- OpenAI Gym
How to create new environments for Gym
cd gym-michigan
pip install -e .- Johan Backman johback@student.chalmers.se
- Hampus Ramström hampusr@student.chalmers.se