ml-agents and ml-agents-snowball-fight

ML-Agents Toolkit is the foundational framework that enables the creation of multi-agent training environments like the Snowball Fight example, making them complements used together rather than alternatives.

ml-agents
70
Verified
Maintenance 10/25
Adoption 10/25
Maturity 25/25
Community 25/25
Maintenance 0/25
Adoption 5/25
Maturity 16/25
Community 14/25
Stars: 19,215
Forks: 4,431
Downloads:
Commits (30d): 0
Language: C#
License:
Stars: 10
Forks: 3
Downloads:
Commits (30d): 0
Language:
License: Apache-2.0
No risk flags
Stale 6m No Package No Dependents

About ml-agents

Unity-Technologies/ml-agents

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.

This toolkit helps game developers and researchers create intelligent characters and systems within Unity games and simulations. You provide a Unity game environment, and the toolkit outputs trained AI agents that can control Non-Player Characters (NPCs), automate game testing, or evaluate design choices. Game developers and AI researchers are the primary users.

game-development AI-research-games NPC-behavior game-testing simulation-training

About ml-agents-snowball-fight

simoninithomas/ml-agents-snowball-fight

A multi-agent environment using Unity ML-Agents Toolkit

This environment provides a simulated 2 vs 2 snowball fight game where four AI agents compete. It helps developers create and train machine learning models for cooperative and adversarial multi-agent behaviors. Input involves configuring the game environment and agent reward functions, and the output is trained AI agents capable of playing the game effectively. This is for AI/ML researchers and game AI developers.

Multi-Agent Reinforcement Learning Game AI Development Cooperative AI Adversarial AI AI Simulation

Scores updated daily from GitHub, PyPI, and npm data. How scores work