README.md

DDPG:Deep Deterministic Policy Gradient_implementation

This is a Tensorflow implementation of the 'Continuous control with Deep Reinforcement learning' paper (Both of the jupyter notebook and python script is used for the 'main' file)

Paper: Continuous control with deep reinforcement learning

Env:Pendulum-v0 (with normalization and OU Noise)

Note:In the title of the above plot,there should be '250 scores' instead of '100 scores'

References: openai/baselines