Skip to content
No description, website, or topics provided.
Branch: master
Clone or download
Latest commit 37ea126 Jan 23, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
experimental_results initial commit Jan 23, 2019
experimental_results_car initial commit Jan 23, 2019
models anonymize Jan 23, 2019
seed_2_data initial commit Jan 23, 2019
tests initial commit Jan 23, 2019
DQN.py running fqe for lake Jan 22, 2019
Pipfile running grid search Jan 18, 2019
README.md Update README.md Jan 23, 2019
car_constraint_values_wo_band.png initial commit Jan 23, 2019
car_main_value.png initial commit Jan 23, 2019
car_main_value_wo_band.png initial commit Jan 23, 2019
car_racing.py running fqe for lake Jan 22, 2019
config_car.py preparing Jan 23, 2019
config_lake.py preparing Jan 23, 2019
env_dqns.py stabilizing fqi Jan 7, 2019
env_nn.py preparing Jan 23, 2019
exact_policy_evaluation.py anonymizing Jan 23, 2019
exponentiated_gradient.py anonymizing Jan 23, 2019
fitted_algo.py anonymizing Jan 23, 2019
fitted_off_policy_evaluation.py anonymizing Jan 23, 2019
fittedq.py anonymizing Jan 23, 2019
fixed_policy.py running fqe for lake Jan 22, 2019
fqe_quality_test.py anonymizing Jan 23, 2019
fqe_quality_test_generalization.py anonymize Jan 23, 2019
fqi_grid_search.py anonymizing Jan 23, 2019
fqi_seed_2_new.py initial commit Jan 23, 2019
frozen_lake.py hello world Dec 30, 2018
inverse_propensity_scoring.py anonymizing Jan 23, 2019
lake_primal_dual_gap.png initial commit Jan 23, 2019
lake_values.png initial commit Jan 23, 2019
lake_values_wo_band.png initial commit Jan 23, 2019
layer_visualizer.py initial commit Jan 23, 2019
mdp_approximator.py anonymizing Jan 23, 2019
model.py anonymizing Jan 23, 2019
neural_network.py anonymizing Jan 23, 2019
optimization_problem.py anonymizing Jan 23, 2019
pi_old_car_cnn_main.hdf5 initial commit Jan 23, 2019
play_car_racing.py initial commit Jan 23, 2019
plot_fqe_quality_test.py initial commit Jan 23, 2019
plot_grid_search.py initial commit Jan 23, 2019
plot_policy_improvement.py initial commit Jan 23, 2019
plot_policy_improvement_v2.py initial commit Jan 23, 2019
plot_results.py initial commit Jan 23, 2019
print_policy.py
replay_buffer.py preparing Jan 23, 2019
run.py anonymizing Jan 23, 2019
stochastic_policy.py anonymizing Jan 23, 2019
thread_safe.py hello world Dec 31, 2018
value_function.py anonymizing Jan 23, 2019

README.md

constrained_batch_policy_learning

*Note: Use the --headless flag if using a server without a display.

Otherwise, to run the main algorithm:

pip install pipenv
pipenv install
pipenv run python run.py -env car --headless

or, for lake,

pipenv run python run.py -env lake --headless
You can’t perform that action at this time.