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