Skip to content

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

Notifications You must be signed in to change notification settings

giulic3/flatland-challenge-marl

Repository files navigation

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.

About

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

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages