Unity Tennis - Multi-Agent Reinforcement Learning (MADDPG)

VIDEO DESCRIPTION:

Play, download and edit the free video Unity Tennis - Multi-Agent Reinforcement Learning (MADDPG).

This project was done as part of the Udacity Deep Reinforcement Learning Nanodegree. MADDPG (Multi-Agent Deep Deterministic Policy Gradient) algorithm was used in this project to teach 2 agents simultaneously to play tennis together in a Unity environment. For this project, I used the Tennis environment.
In this environment, two agents control rackets to bounce a ball over a net. If an agent hits the ball over the net, it receives a reward of +0.1. If an agent lets a ball hit the ground or hits the ball out of bounds, it receives a reward of -0.01. Thus, the goal of each agent is to keep the ball in play.
The observation space consists of 8 variables corresponding to the position and velocity of the ball and racket. Each agent receives its own, local observation. Two continuous actions are available, corresponding to movement toward (or away from) the net, and jumping.
The task is episodic, and in order to solve the environment, agents must get an average score of +0.5 over 100 consecutive episodes, after taking the maximum over both agents.

Download, play and edit free videos and free audios from Unity Tennis - Multi-Agent Reinforcement Learning (MADDPG) using RedcoolMedia.net web apps