Skip to main content

Codebase for the UCI multi agent reinforcement learning framework

A framework for developing large multiplayer reinforcement learning agents that can play free-for-all games. Currently available games are:

  • Tron: A simple snake-like game where the goal is not to crash into the walls.
  • Blokus: A board game of controlling territory with various shaped blocks.
  • Tic Tac Toe: Generalization of tic tac toe to 2, 3, and 4 players.

Requirements

This library requires at least Python 3.6 in order to run correctly. Python 2.7 is not currently supported.

Basic requirements are listed in the requirements.txt and can be installed from PyPi with pip install -r requirements.txt.

Install

Simply run pip install colosseumrl in order to install the latest stable version from Pypi.

Important scripts

python3 -m colosseumrl.matchmaking.MatchmakingServer launches the main matchmaking server for allowing any number of agents to play against each other in a dynamic way. Run python -m rlcompetition.matchmaking.MatchmakingServer -h for more information.

./colosseumrl/examples contains a list of example scripts that will connect to a matchmaking server and launch an example agent.

Metadata

Release files for colosseumrl 1.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for colosseumrl 1.1.0
File Size Uploaded Provenance Actions
colosseumrl-1.1.0.tar.gz 155.9 kB Without provenance Details for colosseumrl-1.1.0.tar.gz

Release files / colosseumrl-1.1.0.tar.gz

Download URL colosseumrl-1.1.0.tar.gz
Size 155.9 kB
Tags Source
SHA-256 checksum
How to use checksums
aa383e9c88cf74fabfae1d2eec05500007e5717fbbd79b0912a2c6e8024ca60d
BLAKE2b-256 checksum
How to use checksums
0b9eec1eb9979b6fbacc2b910f721135ef460c44fee527b46da999e1175f6bff
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/3.1.1 pkginfo/1.5.0.1 requests/2.22.0 setuptools/42.0.2.post20191203 requests-toolbelt/0.9.1 tqdm/4.41.1 CPython/3.7.5

Security for colosseumrl 1.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page