Collection of Deep Reinforcement Learning algorithms.
Dependencies:
Tested with Python 2.7 and Python 3.6
So far:
- DDPG - Deep Deterministic Policy Gradients, evaluated on the Pendulum-v0 environment in OpenAI Gym.
If you have used this code to do something cool, send me a link and a GIF (via email or pull request) and I'll add it
- @keithmgould used the same the DDPG code to solve the inverted Pendulum task in Roboschool.