ddpg-aigym

Deep Deterministic Policy Gradient

Implementation of Deep Deterministic Policy Gradiet Algorithm (Lillicrap et al.arXiv:1509.02971.) in Tensorflow

Revised with python 3.6

The learning curve for InvertedPendulum-v1 environment.

To use different environment

experiment= 'InvertedPendulum-v1' #specify environments here

To use batch normalization

is_batch_norm = True #batch normalization switch

Let me know if there are any issues and clarifications regarding hyperparameter tuning.

Name		Name	Last commit message	Last commit date
Latest commit History 47 Commits
batch_normalization		batch_normalization
tf.gradients_eg		tf.gradients_eg
.gitignore		.gitignore
DDPG.pyc		DDPG.pyc
LICENSE		LICENSE
README.md		README.md
actor_net.py		actor_net.py
actor_net.pyc		actor_net.pyc
actor_net_bn.py		actor_net_bn.py
critic_net.py		critic_net.py
critic_net.pyc		critic_net.pyc
critic_net_bn.py		critic_net_bn.py
ddpg.py		ddpg.py
ddpg.pyc		ddpg.pyc
episode_reward.txt		episode_reward.txt
learning_curve.png		learning_curve.png
main.py		main.py
ou_noise.py		ou_noise.py
result_plot.py		result_plot.py
tensorflow_grad_inverter.py		tensorflow_grad_inverter.py
tensorflow_session.py		tensorflow_session.py