https://github.com/giulic3/flatland-challenge-marl
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
https://github.com/giulic3/flatland-challenge-marl
deep-q-learning deep-reinforcement-learning multi-agent-reinforcement-learning pytorch
Last synced: over 1 year ago
JSON representation
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
- Host: GitHub
- URL: https://github.com/giulic3/flatland-challenge-marl
- Owner: giulic3
- License: mit
- Created: 2019-07-07T17:03:22.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2020-01-22T17:03:56.000Z (over 6 years ago)
- Last Synced: 2025-03-20T15:11:54.448Z (over 1 year ago)
- Topics: deep-q-learning, deep-reinforcement-learning, multi-agent-reinforcement-learning, pytorch
- Language: Python
- Homepage:
- Size: 37.9 MB
- Stars: 12
- Watchers: 3
- Forks: 0
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE.md
Awesome Lists containing this project
README
# flatland-challenge-marl
This repository contains the code issued to the Flatland competition in the structure explained in the
[flatland-challenge-starter-kit](https://github.com/AIcrowd/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](https://arxiv.org/abs/1710.02298) for multi-agent systems.
## Acknowledgements
The code for Rainbow was adapted to MAS from [Kaixhin/Rainbow](https://github.com/Kaixhin/Rainbow).