Skip to content

Latest commit

 

History

History
10 lines (6 loc) · 416 Bytes

README.md

File metadata and controls

10 lines (6 loc) · 416 Bytes

DDPG

Implementation of deep deterministic policy gradient algorithm using PyTorch. Tested in OpenAI Gym Pendulum-v0 environment.

Actor behavior after 2000 episodes

pendulum_2000.mp4

Actor behavior after 4000 episodes

pendulum_4000.mp4