Light

giulic3 / flatland-challenge-marl Goto Github PK

Proposed solution to the Flatland challenge (https://www.aicrowd.com/challenges/flatland-challenge), solving the Vehicle Rescheduling Problem (VRSP) on trains using Multi-Agent-Reinforcement-Learning

License: MIT License

Python 99.99% Shell 0.01%

deep-reinforcement-learning deep-q-learning multi-agent-reinforcement-learning pytorch

flatland-challenge-marl's Introduction

flatland-challenge-marl

This repository contains the code issued to the Flatland competition in the structure explained in the flatland-challenge-starter-kit.

The relevant directories are:

cnn_globalobs - contains an approach based on CNN and (custom) global observations
fc_treeobs - contains an approach based on tree observations (for both single and multi-agent setting)
src/ - contains code with graph observations and local observations
src/rainbow/ - contains code of Rainbow for multi-agent systems.

Acknowledgements

The code for Rainbow was adapted to MAS from Kaixhin/Rainbow.

flatland-challenge-marl's People

Contributors

Stargazers

Watchers

flatland-challenge-marl's Issues

did your cnn for global observations converge?

Hello! i ran your solution for the global observation and i didn't see any signs of the agent converging. I set 8000 episodes, was not enough?

Invalid flatalnd-rl version

Hey, I strongly suspect your version of flatland-rl listed in environment.yaml is too new.

I did: conda env create -n flatland-01 --file environment.yaml

I expected:

To be able to run cnn_globalobs/traning.py right after conda activate flatland-01

What happened:

For starters, RailEnv's init function changed so it no longer accepts stochastic_data and program crashes

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.