Example DDPG implementation with ReLAx
This repository contains an implementation of deep deterministic policy gradient (DDPG) with ReLAx.
DDPG actor was trained on InvertedPendulum-v2 Mujoco Gym environment for 100k env-steps.
The graph of average return vs environment step is shown below (logs done every 10k steps):
The distribution of estimated Q-values vs data Q-values is shown below:
Resulting Policy: