Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/cool-RR/marley
A framework for multi-agent reinforcement learning.
https://github.com/cool-RR/marley
ai hacktoberfest keras machine-learning python q-learning reinforcement-learning tensorflow
Last synced: 3 months ago
JSON representation
A framework for multi-agent reinforcement learning.
- Host: GitHub
- URL: https://github.com/cool-RR/marley
- Owner: cool-RR
- License: mit
- Created: 2020-10-06T12:41:44.000Z (over 3 years ago)
- Default Branch: master
- Last Pushed: 2022-05-21T12:17:52.000Z (about 2 years ago)
- Last Synced: 2024-03-18T01:02:57.931Z (3 months ago)
- Topics: ai, hacktoberfest, keras, machine-learning, python, q-learning, reinforcement-learning, tensorflow
- Language: Python
- Homepage:
- Size: 30.7 MB
- Stars: 271
- Watchers: 13
- Forks: 27
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Lists
- my-awesome-stars - cool-RR/marley - A framework for multi-agent reinforcement learning. (Python)
- awesome-stars - marley - agent reinforcement learning. | cool-RR | 271 | (Python)
- awesome-stars - cool-RR/marley - A framework for multi-agent reinforcement learning. (Python)
README
# Marley #
Marley is a framework for multi-agent reinforcement learning. It lets you design a game and run experiments with multiple AI-powered agents playing that game.
**Marley isn't ready for use yet; it works for my research purposes, but I haven't yet made the work needed to make it easy to understand for others.** If you're still interested in using it, feel free to read the code or [email me](mailto:[email protected]) for help.
I'm using Marley in my research mission to use machine learning to understand human society. I want to produce emergent reciprocation in selfish RL agents and use that to show social behavior. [Talk video](https://youtu.be/WMVqYYarFkQ), [slides](https://docs.google.com/presentation/d/1uBV2VkCfds_K3Aj7JimK1aE22AJSmLVoOg5oR4pOJU4/), [sign up for updates](https://groups.google.com/g/ram-rachum-research-announce).
I hope to make Marley easier to use soon.
## GridRoyale ##
## [View the live version here!](https://grid-royale.herokuapp.com/) ##
**GridRoyale** is a life simulation. It's a case study that's bundled with Marley.
GridRoyale is similar to [Game of Life](https://en.wikipedia.org/wiki/Conway%27s_Game_of_Life) or
[GridWorld](https://towardsdatascience.com/reinforcement-learning-implement-grid-world-from-scratch-c5963765ebff),
except I added game mechanics to encourage the players to behave socially. These game mechanics are
similar to those in the [battle royale](https://en.wikipedia.org/wiki/Battle_royale_game) genre of
computer games, which is why it's called GridRoyale.
Players get 10 points for eating food, i.e. the dots that regenerate randomly. Players lose 5 points for colliding with other agents or walls. Players lose 10 points for being shot.
# How to run GridRoyale #
Installation:
```console
$ pip install marley
```
Run the server:
```console
$ marley grid_royale demo
```
This will automatically open a browser window and show you your simulation.