Deep Reinforcement Learning Nanodegree Udacity

This repository contains project files with solutions for Udacity's Deep Reinforcement Learning Nanodegree program.

Projects

Navigation

P1_Navigation

For this project, we train an agent to navigate and collect bananas in a large, square world using Deep Q-Network (DQN).

Continuous Control

P2_Continuous Control

For this project, we train a double-jointed arm agent to follow a target location using Deeo Distributed Policy Gradient (DDPG).

Collaboration and Competition

P3_Collaboration Competition

For this project, we train multiple (a pair of) agents to play tennis using DDPG with shared replay buffer.