jason-RL adds a reinforcement learning layer to the Jason multi-agent framework, allowing AgentSpeak BDI agents to learn action-selection policies via reward feedback. It implements Q-learning and SARSA algorithms, supports configuration of learning parameters (learning rate, discount factor, exploration strategy), and logs training metrics. By defining reward functions in agent plans and running simulations, developers can observe agents improve decision making over time, adapting to changing environments without manual policy coding.

MARFT is a Python-based LLMs, enabling reproducible experiments and rapid prototyping of collaborative AI systems.

MineLand provides a flexible 3D sandbox environment inspired by Minecraft for training reinforcement learning agents. It features Gym-compatible APIs for seamless integration with existing RL libraries such as Stable Baselines, RLlib, and custom implementations. Users gain access to a library of tasks, including resource collection, navigation, and construction challenges, each with configurable difficulty and reward structures. Real-time rendering, multi-agent scenarios, and headless modes allow for scalable training and benchmarking. Developers can design new maps, define custom reward functions, and plugin additional sensors or controls. MineLand’s open-source codebase fosters reproducible research, collaborative development, and rapid prototyping of AI agents in complex virtual worlds.

mini-AlphaStar demystifies the complex AlphaStar architecture by offering an accessible, open-source PyTorch framework for StarCraft II AI development. It features spatial feature encoders for screen and minimap inputs, non-spatial feature processing, LSTM memory modules, and separate policy and value networks for action selection and state evaluation. Using imitation learning to bootstrap and reinforcement learning with self-play for fine-tuning, it supports environment wrappers compatible with StarCraft II via pysc2, logging through TensorBoard, and configurable hyperparameters. Researchers and students can generate datasets from human gameplay, train models on custom scenarios, evaluate agent performance, and visualize learning curves. The modular codebase enables easy experimentation with network variants, training schedules, and multi-agent setups. Designed for education and prototyping rather than production deployment.

Multi-Agent Inspection Simulation provides a comprehensive framework for simulating and training multiple autonomous agents to perform inspection tasks cooperatively within Unity 3D environments. It integrates with the Unity ML-Agents toolkit, offering configurable scenes with inspection targets, adjustable reward functions, and agent behavior parameters. Researchers can script custom environments, define the number of agents, and set training curricula via Python APIs. The package supports parallel training sessions, TensorBoard logging, and customizable observations including raycasts, camera feeds, and positional data. By adjusting hyperparameters and environment complexity, users can benchmark reinforcement learning algorithms on coverage, efficiency, and coordination metrics. The open-source codebase encourages extension for robotics prototyping, cooperative AI research, and educational demonstrations in multi-agent systems.

Multi-Agent Surveillance offers a flexible simulation framework where multiple AI agents act as predators or evaders in a discrete grid world. Users can configure environment parameters such as grid dimensions, number of agents, detection radii, and reward structures. The repository includes Python classes for agent behavior, scenario generation scripts, built-in visualization via matplotlib, and seamless integration with popular reinforcement learning libraries. This makes it easy to benchmark multi-agent coordination, develop custom surveillance strategies, and conduct reproducible experiments.

Multi-Agent Drone Environment is a Python package offering a customizable multi-agent simulation for UAV swarms, built on OpenAI Gym and PyBullet. Users define multiple drone agents with kinematic and dynamic models to explore cooperative tasks such as formation flying, target tracking, and obstacle avoidance. The environment supports modular task configuration, realistic collision detection, and sensor emulation, while allowing custom reward functions and decentralized policies. Developers can integrate their own reinforcement learning algorithms, evaluate performance under varied scenarios, and visualize agent trajectories and metrics in real time. Its open-source design encourages community contributions, making it ideal for research, teaching, and prototyping advanced multi-agent control solutions.

The Multi-Agent Autonomous Waste Collection System is a research-driven platform that employs multi-agent reinforcement learning to train individual waste-collecting robots to collaborate on route planning. Agents learn to avoid redundant coverage, minimize travel distance, and respond to dynamic waste generation patterns. Built in Python, the system integrates a simulation environment for testing and refining policies before real-world deployment. Users can configure map layouts, waste drop-off points, agent sensors, and reward structures to tailor behavior to specific urban areas or operational constraints.

This open-source project delivers a complete multi-agent reinforcement learning framework built on PyTorch and Unity ML-Agents. It offers decentralized DDPG algorithms, environment wrappers, and training scripts. Users can configure agent policies, critic networks, replay buffers, and parallel training workers. Logging hooks allow TensorBoard monitoring, while modular code supports custom reward functions and environment parameters. The repository includes sample Unity scenes demonstrating collaborative navigation tasks, making it ideal for extending and benchmarking multi-agent scenarios in simulation.

Multi-Agent Visual Tracking implements a distributed tracking system composed of intelligent agents that communicate to improve accuracy and robustness in video object tracking. Agents run convolutional neural networks for detection, share observations to handle occlusions, and adjust tracking parameters through reinforcement learning. Compatible with popular video datasets, it supports both training and real-time inference. Users can easily integrate it into existing pipelines and extend agent behaviors for custom applications.

MultiAgent-Systems-StarCraft2-PySC2-Raw offers a complete toolkit for developing, training, and evaluating multiple AI agents in StarCraft II. It exposes low-level controls for unit movement, targeting, and abilities, while allowing flexible reward design and scenario configuration. Users can easily plug in custom neural network architectures, define team-based coordination strategies, and record metrics. Built on top of PySC2, it supports parallel training, checkpointing, and visualization, making it ideal for advancing research in cooperative and adversarial multi-agent reinforcement learning.

Multiagent_system offers a comprehensive toolkit for constructing and managing multi-agent environments. Users can define custom simulation scenarios, specify agent behaviors, and leverage pre-implemented algorithms such as DQN, PPO, and MADDPG. The framework supports synchronous and asynchronous training, enabling agents to interact concurrently or in turn-based setups. Built-in communication modules facilitate message passing between agents for cooperative strategies. Experiment configuration is streamlined via YAML files, and results are logged automatically to CSV or TensorBoard. Visualization scripts help interpret agent trajectories, reward evolution, and communication patterns. Designed for research and production workflows, Multiagent_system seamlessly scales from single-machine prototypes to distributed training on GPU clusters.

MultiAgentes provides a modular architecture for defining environments and agents, supporting synchronous and asynchronous multi-agent interactions. It includes base classes for environments and agents, predefined scenarios for cooperative and competitive tasks, tools for customizing reward functions, and APIs for agent communication and observation sharing. Visualization utilities allow real-time monitoring of agent behaviors, while logging modules record performance metrics for analysis. The framework integrates seamlessly with Gym-compatible reinforcement learning libraries, enabling users to train agents using existing algorithms. MultiAgentes is designed for extensibility, allowing developers to add new environment templates, agent types, and communication protocols to suit diverse research and educational use cases.

MultiAgentPacman offers a Python-based game environment where users can implement, visualize, and benchmark multiple AI agents in the Pacman domain. It supports adversarial search algorithms like minimax, expectimax, alpha-beta pruning, as well as custom reinforcement learning or heuristic-based agents. The framework includes a simple GUI, command-line controls, and utilities to log game statistics and compare agent performance under competitive or cooperative scenarios.

MultiAgentSystems is designed to simplify the process of building and evaluating multi-agent reinforcement learning (MARL) applications. The platform includes implementations of state-of-the-art algorithms like MADDPG, QMIX, VDN, and centralized training with decentralized execution. It features modular environment wrappers compatible with OpenAI Gym, communication protocols for agent interaction, and logging utilities to track metrics such as reward shaping and convergence rates. Researchers can customize agent architectures, tune hyperparameters, and simulate settings including cooperative navigation, resource allocation, and adversarial games. With built-in support for PyTorch, GPU acceleration, and TensorBoard integration, MultiAgentSystems accelerates experimentation and benchmarking in collaborative and competitive multi-agent domains.

NavGround Learning provides a comprehensive toolkit for developing and benchmarking reinforcement learning agents in navigation tasks. It supports multi-agent simulation, collision modeling, and customizable sensors and actuators. Users can select from predefined policy templates or implement custom architectures, train with state-of-the-art RL algorithms, and visualize performance metrics. Its integration with OpenAI Gym and Stable Baselines3 simplifies experiment management, while built-in logging and visualization tools allow in-depth analysis of agent behavior and training dynamics.

OpenSpiel is a research framework that provides a wide range of environments (from simple matrix games to complex board games such as Chess, Go, and Poker) and implements various reinforcement learning and search algorithms (e.g., value iteration, policy gradient methods, MCTS). Its modular C++ core and Python bindings allow users to plug in custom algorithms, define new games, and compare performance across standard benchmarks. Designed for extensibility, it supports single and multi-agent settings, enabling study of cooperative and competitive scenarios. Researchers leverage OpenSpiel to prototype algorithms quickly, run large-scale experiments, and share reproducible code.

Pits and Orbs is an open-source reinforcement learning environment implemented in Python, offering a turn-based multi-agent grid-world where agents pursue objectives and face environmental hazards. Each agent must navigate a customizable grid, avoid randomly placed pits that penalize or terminate episodes, and collect orbs for positive rewards. The environment supports both competitive and cooperative modes, enabling researchers to explore varied learning scenarios. Its simple API integrates seamlessly with popular RL libraries like Stable Baselines or RLlib. Key features include adjustable grid dimensions, dynamic pit and orb distributions, configurable reward structures, and optional logging for training analysis.

Poke-Env is designed to streamline the creation and evaluation of AI agents for Pokémon Showdown battles by providing a comprehensive Python interface. It handles communication with the Pokémon Showdown server, parses game state data, and manages turn-by-turn actions through an event-driven architecture. Users can extend base player classes to implement custom strategies using reinforcement learning or heuristic algorithms. The framework offers built-in support for battle simulations, parallelized matchups, and detailed logging of actions, rewards, and outcomes for reproducible research. By abstracting low-level networking and parsing tasks, Poke-Env allows AI researchers and developers to focus on algorithm design, performance tuning, and comparative benchmarking of battle strategies.

PyBrain, short for Python-Based Reinforcement Learning, Artificial Intelligence, and Neural Networks Library, is a modular and open-source library designed for machine learning tasks. It supports building neural networks, reinforcement learning, and other AI algorithms. With its powerful and easy-to-use algorithms, PyBrain provides a valuable tool for both developers and researchers aiming to tackle various machine learning problems. The library integrates smoothly with other Python libraries and is suitable for tasks ranging from simple supervised learning to complex reinforcement learning scenarios.