ml-agents and Crowds-and-ML-Agents

ML-Agents is the foundational toolkit that B builds upon—B is a specialized application/research project that uses ML-Agents as its core dependency to implement crowd simulation with reinforcement and imitation learning, making them complements rather than competitors.

ml-agents
79
Verified
Crowds-and-ML-Agents
25
Experimental
Maintenance 10/25
Adoption 19/25
Maturity 25/25
Community 25/25
Maintenance 0/25
Adoption 5/25
Maturity 9/25
Community 11/25
Stars: 19,215
Forks: 4,431
Downloads: 12,910
Commits (30d): 0
Language: C#
License:
Stars: 12
Forks: 2
Downloads:
Commits (30d): 0
Language: ShaderLab
License: GPL-3.0
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.

Implements PyTorch-based algorithms (PPO, SAC, MA-POCA) for single and multi-agent scenarios, with support for imitation learning, curriculum learning, and environment randomization. Provides native cross-platform inference through its Inference Engine and exposes Unity environments as standard Python APIs (Gym, PettingZoo) for seamless integration with the broader ML ecosystem. Enables on-demand agent decision-making and concurrent training across multiple environment instances for scalable experiment iteration.

About Crowds-and-ML-Agents

apanay20/Crowds-and-ML-Agents

Training of agents using Reinforcement and Imitation Learning to simulate human crowds behavior, using Unity and ML-Agents Toolkit.

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