udacity-drlnd
Udacity Deep Reinforcement Learning Projects
Project 1: Navigation
This project contains code for training a Deep Q-Network agent to navigate (and collect bananas!) in a large, square world.
Project 2: Continuous Control
This project contains code for training a Deep Deterministic Policy Gradient (DDPG) agent to control a reacher arm that is tracking a positional target.
Project 3: Tennis Multi-Agent Control
This project contains code for training Deep Deterministic Policy Gradient (DDPG) agents to control to play tennis against each other.