Mava is a JAX-based open-source library for developing, training, and evaluating multi-agent reinforcement learning systems. It offers pre-built implementations of cooperative and competitive algorithms such as MAPPO and MADDPG, along with configurable training loops that support single-node and distributed workflows. Researchers can import environments from PettingZoo or define custom environments, then use Mava’s modular components for policy optimization, replay buffer management, and metric logging. The framework’s flexible architecture allows seamless integration of new algorithms, custom observation spaces, and reward structures. By leveraging JAX’s auto-vectorization and hardware acceleration capabilities, Mava ensures efficient large-scale experiments and reproducible benchmarking across various multi-agent scenarios.

MultiAgentPuzzleSolver provides a modular environment where independent AI agents work together to solve puzzles such as sliding tiles, Rubik’s Cube, and logic grids. Agents share state information, negotiate subtask assignments, and apply diverse heuristics to explore the solution space more effectively than single-agent approaches. Developers can plug in new agent behaviors, customize communication protocols, and add novel puzzle definitions. The framework includes tools for real-time visualization of agent interactions, performance metrics collection, and experiment scripting. It supports Python 3.8+, standard libraries, and popular ML toolkits for seamless integration into research projects.