DDPG-PyTorch

Deep Deterministic Policy Gradient implemented in PyTorch for DeepMind Control Suite

This repository contains the code to implement the algorithm in the paper Continuous Control with Deep Reinforcement Learning. The algorithm presents a method to perform Q-learning in continuous action spaces. The code contains the implementation on DeepMind Control Suite simulations.

BLOGPOST: https://sameera-lanka.com/blog/2018/2/19/deep-deterministic-policy-gradientpytorch-dm-control-suite