Reimplementing DDPG from Continuous Control with Deep Reinforcement Learning based on OpenAI Gym and Tensorflow
http://arxiv.org/abs/1509.02971
There are still some issues to be solved in this implementation. The performance is still bad. I hope anybody who study DDPG could help figure out how to improve the performance.
git clone https://github.com/songrotek/DDPG.git
cd DDPG
python gym_ddpg.py