https://github.com/himelbrand/marl-qtran

An implementation of QTRAN algorithm for Multiagent Reinforcement Learning.
https://github.com/himelbrand/marl-qtran

multiagent-reinforcement-learning reinforcement-learning reinforcement-learning-algorithms

Last synced: about 2 months ago
JSON representation

An implementation of QTRAN algorithm for Multiagent Reinforcement Learning.

• Host: GitHub
• URL: https://github.com/himelbrand/marl-qtran
• Owner: himelbrand
• Created: 2021-01-31T12:58:15.000Z (over 5 years ago)
• Default Branch: main
• Last Pushed: 2021-06-16T14:18:55.000Z (about 5 years ago)
• Last Synced: 2024-01-28T21:39:59.317Z (over 2 years ago)
• Topics: multiagent-reinforcement-learning, reinforcement-learning, reinforcement-learning-algorithms
• Language: Python
• Homepage:
• Size: 18.9 MB
• Stars: 5
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Multiagent Reinforcment learning - QTRAN

This repository is an implementation of [QTRAN](https://arxiv.org/pdf/1905.05408.pdf) paper to play 2 games from the [@PettingZoo](https://github.com/PettingZoo-Team/PettingZoo) project which provides Multiagent enviorments for reinforcment learning.

## The two games are

* [Pistonball](https://www.pettingzoo.ml/butterfly/pistonball)

* [KAZ](https://www.pettingzoo.ml/butterfly/knights_archers_zombies)

## The Architecture Visualized

![img1](https://drive.google.com/uc?export=view&id=1L62gverInlESp_4Ne6OeiOYxPQBKF97Z)

![img2](https://drive.google.com/uc?export=view&id=1q4wUwTh2LHax4Jw3wWiygX0QxSqw9MMA)

### Note that this readme is still a WIP

Plus the code files needs some rearranging