GflowsForSimulation (In progress)

This projects builds off the work in ¹, I am using the AflowNet with the goal of optimizing exploration in the simulated military training environment.

Leveraging Graph Networks to Model Environments in Reinforcement Learning. link. ↩

Name		Name	Last commit message	Last commit date
Latest commit History 54 Commits
.vscode		.vscode
__pycache__		__pycache__
graph_scout		graph_scout
model		model
models		models
sigma_graph		sigma_graph
.DS_Store		.DS_Store
.gitignore		.gitignore
Dockerfile		Dockerfile
README.md		README.md
__init__.py		__init__.py
env.yml		env.yml
graph_tools.ipynb		graph_tools.ipynb
losses.py		losses.py
requirements.txt		requirements.txt
toy_example.ipynb		toy_example.ipynb
toy_example.py		toy_example.py
train.ipynb		train.ipynb
train.py		train.py
train_fcn_fig_8.py		train_fcn_fig_8.py
train_fcn_simple_reward.ipynb		train_fcn_simple_reward.ipynb
train_fcn_simple_reward.py		train_fcn_simple_reward.py
train_fig_8.ipynb		train_fig_8.ipynb
train_fig_8.py		train_fig_8.py
train_stop_test.py		train_stop_test.py
trajectory.py		trajectory.py
vis_tools.ipynb		vis_tools.ipynb