DEf-MARL (Decentralized Execution Framework for Multi-Agent Reinforcement Learning) provides a robust infrastructure to execute and train cooperative agents without centralized controllers. It leverages peer-to-peer communication protocols to share policies and observations among agents, enabling coordination through local interactions. The framework integrates seamlessly with common RL toolkits like PyTorch and TensorFlow, offering customizable environment wrappers, distributed rollout collection, and gradient synchronization modules. Users can define agent-specific observation spaces, reward functions, and communication topologies. DEf-MARL supports dynamic agent addition and removal at runtime, fault-tolerant execution by replicating critical state across nodes, and adaptive communication scheduling to balance exploration and exploitation. It accelerates training by parallelizing environment simulations and reducing central bottlenecks, making it suitable for large-scale MARL research and industrial simulations.

VMAS is a comprehensive toolkit for building and training multi-agent systems using deep reinforcement learning. It supports GPU-based parallel simulation of hundreds of environment instances, enabling high-throughput data collection and scalable training. VMAS includes implementations of popular MARL algorithms like PPO, MADDPG, QMIX, and COMA, along with modular policy and environment interfaces for rapid prototyping. The framework facilitates centralized training with decentralized execution (CTDE), offers customizable reward shaping, observation spaces, and callback hooks for logging and visualization. With its modular design, VMAS seamlessly integrates with PyTorch models and external environments, making it ideal for research in cooperative, competitive, and mixed-motive tasks across robotics, traffic control, resource allocation, and game AI scenarios.

AutoDRIVE Cooperative MARL is an open-source framework designed to train and deploy cooperative multi-agent reinforcement learning (MARL) policies for autonomous driving tasks. It integrates with realistic simulators to model traffic scenarios like intersections, highway platooning, and merging. The framework implements centralized training with decentralized execution, enabling vehicles to learn shared policies that maximize overall traffic efficiency and safety. Users can configure environment parameters, choose from baseline MARL algorithms, visualize training progress, and benchmark agent coordination performance.