GitHub - Pdbz199/Koopman-RL-Old: Data-driven Koopman control theory applied to reinforcement learning!

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 525 Commits
final		final
koopman_tensor		koopman_tensor
misc		misc
optimal_agent		optimal_agent
random_agent		random_agent
.gitignore		.gitignore
Control Algorithms 10.28.2021.ipynb		Control Algorithms 10.28.2021.ipynb
Control Algorithms 11.04.2021.ipynb		Control Algorithms 11.04.2021.ipynb
DoubleWell_GenerateData.py		DoubleWell_GenerateData.py
Koopman RL 3-26.ipynb		Koopman RL 3-26.ipynb
Koopman RL 3-26.py		Koopman RL 3-26.py
Koopman RL 4-15.ipynb		Koopman RL 4-15.ipynb
Koopman RL 4-15.py		Koopman RL 4-15.py
Koopman RL 5-5.ipynb		Koopman RL 5-5.ipynb
Koopman RL 5-5.py		Koopman RL 5-5.py
Koopman RL 6-10.ipynb		Koopman RL 6-10.ipynb
Q_table.npy		Q_table.npy
RL.py		RL.py
__init__.py		__init__.py
algorithms.py		algorithms.py
algorithmsv2.py		algorithmsv2.py
algorithmsv2_parallel.py		algorithmsv2_parallel.py
animation.gif		animation.gif
auxiliaries.py		auxiliaries.py
base.py		base.py
bellman-weights.npy		bellman-weights.npy
brownian.py		brownian.py
cartpole-actor-critic.py		cartpole-actor-critic.py
cartpole_discrete_koopman_actor_critic.py		cartpole_discrete_koopman_actor_critic.py
cartpole_reward.py		cartpole_reward.py
conda-requirements.txt		conda-requirements.txt
conda-requirements.yml		conda-requirements.yml
domain.py		domain.py
edmd-rff-kernel.py		edmd-rff-kernel.py
estimate-drift-and-variance.py		estimate-drift-and-variance.py
estimate_L.py		estimate_L.py
faster_integration.py		faster_integration.py
gedmd.py		gedmd.py
gedmdTest.py		gedmdTest.py
general_model.py		general_model.py
generator.py		generator.py
gradient.py		gradient.py
hjb-koopman-control.py		hjb-koopman-control.py
iterative-lqr.py		iterative-lqr.py
kernel-koopman.py		kernel-koopman.py
kernels.py		kernels.py
klus_algos.py		klus_algos.py
koopman-control.py		koopman-control.py
koopman-taxi.py		koopman-taxi.py
koopman-tensor-cartpole.py		koopman-tensor-cartpole.py
koopman.py		koopman.py
lambda-labs-requirements.txt		lambda-labs-requirements.txt
lqr-cartpole-swing-up.py		lqr-cartpole-swing-up.py
multi-koopman.py		multi-koopman.py
observables.py		observables.py
observables.py.BAK		observables.py.BAK
pip-requirements.txt		pip-requirements.txt
predict_brownian.py		predict_brownian.py
random-taxi-agent.py		random-taxi-agent.py
randomRL.py		randomRL.py
rrr.py		rrr.py
scrap.py		scrap.py
simple_env.py		simple_env.py
sindy.py		sindy.py
state-action-inputs.npy		state-action-inputs.npy
state-action-outputs.npy		state-action-outputs.npy
system_identification.py		system_identification.py
systems.py		systems.py
tensor-approach.py		tensor-approach.py
test_model.py		test_model.py
test_mppi.py		test_mppi.py
test_observables.py		test_observables.py
tf_algorithmsv2.py		tf_algorithmsv2.py
tf_observables.py		tf_observables.py
tools.py		tools.py
utilities.py		utilities.py
williams-paper.py		williams-paper.py

About

Data-driven Koopman control theory applied to reinforcement learning!

Activity

23 stars

4 watching

6 forks

Report repository

Releases

No releases published

Packages

No packages published

Pdbz199/Koopman-RL-Old

Folders and files

Latest commit

History