Deep Reinforcement Learning multi agent that solves the Tennis environment, as stated in the third project of Udacity DRL Nanodegree.

Trained a pair of agents to play tennis. Reinforcement Learning methods were used along with various Deep Learning algorithms.

Two deep-reinforcement learning agents that play tennis.

The third project of Udacity Deep Reinforcement Learning Nanodegree

Implement MADDPG to solve Collaboration and Competition problem in Unity

My solutions to the projects within the Udacity Deep Reinforcement Learning Nanodegree.

Udacity DRL nanodegree project 3 submission

Train the model using Multi Agent DDPG of deep reinforcement learning with Tennis Environment in the Unity Agents

Usage of Unity ML-Agents train two agents to play tennis

Training a pair of competing RL agents to play Tennis using MADDPG algorithm

Using MADDPG for solving Multi Agent Based Unity Environment

My code and report of Udacity DRL nanodegree project3 Collaboration and Competition

a deep reinforcement learning project for which two agents have to learn to collaborate to keep the ball in a game of Tennis in the game for as long as possible

The state-of-the-art in multi-agent Reinforcement Learning is the MADDPG algorithm which utilises DDPG actor-critic neural networks where each agent uses centralized critic training but decentralized actor execution, and is capable of learning either cooperative or competitive environments. This is demonstrated on the Unity Tennis Environment.

Project 3 of Udacity's Deep Reinforcement Learning nanodegree program

The pytorch implementation of maddpg

Implementation of MADDPG for cooperative-competitive multi-agent environments

Using MADDPG algorithm to solve the unity tennis environment.