Wireless Sensor Network Embedding using Reinforcement Learning

If you have nix installed (for dependency management), you can run the training with

nix-shell --run 'python3 experiments/default.py'

or specify any other experiment. Evaluation can be run with

nix-shell --run 'python3 evaluate.py <target dir> <pickled model>'

Name		Name	Last commit message	Last commit date
Latest commit History 324 Commits
experiments		experiments
marvelo_data		marvelo_data
results		results
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
baseline_agent.py		baseline_agent.py
default.nix		default.nix
dqn_agent.py		dqn_agent.py
draw_embedding.py		draw_embedding.py
embedding.py		embedding.py
embedding_paper.py		embedding_paper.py
embedding_test.py		embedding_test.py
evaluate.py		evaluate.py
features.py		features.py
features_test.py		features_test.py
generator.py		generator.py
gym_environment.py		gym_environment.py
hyperparameters.py		hyperparameters.py
infrastructure.py		infrastructure.py
log_parser.py		log_parser.py
marvelo_adapter.py		marvelo_adapter.py
observation.py		observation.py
overlay.py		overlay.py
peg_size_experiment.py		peg_size_experiment.py
profile.py		profile.py
pylintrc		pylintrc
q_network.py		q_network.py
tf_util.py		tf_util.py
visualization.py		visualization.py
wsignal.py		wsignal.py
wsignal_test.py		wsignal_test.py

Provide feedback