/ddpg-her-pytorch

Implementation of the Hindsight Experience Replay (HER) algorithm using PyTorch. Utilizes Deep Deterministic Policy Gradients for off-policy optimization of RL agents in continuous action spaces.

Primary LanguagePythonGNU General Public License v3.0GPL-3.0

DDPG+HER-PyTorch

Implementation of the Hindsight Experience Replay algorithm using PyTorch. Utilizes Deep Deterministic Policy Gradients for off-policy optimization of the RL agent -- hence, DDPG+HER. Includes (for now) just one pre-trained example agent (FetchReach-v1), as well as a training script for creating new agents.

FetchReach-v1 Agent

DDPG+HER FetchReach-v1 Animation