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.

PyGame Learning Environment (PLE) is an open-source Python framework designed to simplify the development, testing, and benchmarking of reinforcement learning agents within custom game scenarios. It provides a collection of lightweight Pygame-based games with built-in support for agent observations, discrete and continuous action spaces, reward shaping, and environment rendering. PLE features an easy-to-use API compatible with OpenAI Gym wrappers, enabling seamless integration with popular RL libraries such as Stable Baselines and TensorForce. Researchers and developers can customize game parameters, implement new games, and leverage vectorized environments for accelerated training. With active community contributions and extensive documentation, PLE serves as a versatile platform for academic research, education, and real-world RL application prototyping.

Reinforcement Learning Agents for PettingZoo Games is a Python-based code library delivering off-the-shelf DQN, PPO, and A2C algorithms for multi-agent reinforcement learning on PettingZoo environments. It features standardized training and evaluation scripts, configurable hyperparameters, integrated TensorBoard logging, and support for both competitive and cooperative games. Researchers and developers can clone the repo, adjust environment and algorithm parameters, run training sessions, and visualize metrics to benchmark and iterate quickly on their multi-agent RL experiments.

simple_rl is a minimalistic Python library designed to streamline reinforcement learning research and education. It provides a consistent API for defining environments and agents, with built-in support for common RL paradigms including Q-learning, Monte Carlo methods, and dynamic programming algorithms like value and policy iteration. The framework includes sample environments such as GridWorld, MountainCar, and Multi-Armed Bandits, facilitating hands-on experimentation. Users can extend base classes to implement custom environments or agents, while utility functions handle logging, performance tracking, and policy evaluation. simple_rl's lightweight architecture and clear codebase make it ideal for rapid prototyping, teaching RL fundamentals, and benchmarking new algorithms in a reproducible, easy-to-understand environment.

RL Shooter is a Python-based framework that integrates ViZDoom with OpenAI Gym APIs to create a flexible reinforcement learning environment for FPS games. Users can define custom scenarios, maps, and reward structures to train agents on navigation, target detection, and shooting tasks. With configurable observation frames, action spaces, and logging facilities, it supports popular deep RL libraries such as Stable Baselines and RLlib, enabling clear performance tracking and reproducibility across experiments.

VacuumWorld is an open-source simulation platform designed to facilitate the development and evaluation of multi-agent reinforcement learning algorithms. It provides grid-based environments where virtual vacuum cleaner agents operate to detect and remove dirt patches across customizable layouts. Users can adjust parameters such as grid size, dirt distribution, stochastic movement noise, and reward structures to model diverse scenarios. The framework includes built-in support for agent communication protocols, real-time visualization dashboards, and logging utilities for performance tracking. With simple Python APIs, researchers can quickly integrate their RL algorithms, compare cooperative or competitive strategies, and conduct reproducible experiments, making VacuumWorld ideal for academic research and teaching.

SelfDrivingCarSimulator is a lightweight Python framework built on Pygame that offers a 2D driving environment for training autonomous vehicle agents using reinforcement learning. It supports customizable track layouts, configurable sensor models (like LiDAR and camera emulation), real-time visualization, and data logging for performance analysis. Developers can integrate their RL algorithms, adjust physics parameters, and monitor metrics such as speed, collision rate, and reward functions to iterate quickly on self-driving research and educational projects.

Shepherding is an open-source simulation framework designed for reinforcement learning researchers and developers to study and implement multi-agent herding tasks. It provides a Gym-compatible environment where agents can be trained to perform behaviors such as flanking, collecting, and dispersing target groups across continuous or discrete spaces. The framework includes modular reward shaping functions, environment parameterization, and logging utilities for monitoring training performance. Users can define obstacles, dynamic agent populations, and custom policies using TensorFlow or PyTorch. Visualization scripts generate trajectory plots and video recordings of agent interactions. Shepherding’s modular design allows seamless integration with existing RL libraries, enabling reproducible experiments, benchmarking of novel coordination strategies, and rapid prototyping of AI-driven herding solutions.

MultiAgentModel provides a unified API to define custom environments and agent classes for multi-agent scenarios. Developers can specify observation and action spaces, reward structures, and communication channels. Built-in support for popular RL algorithms like PPO, DQN, and A2C allows training with minimal configuration. Real-time visualization tools help monitor agent interactions and performance metrics. The modular architecture ensures easy integration of new algorithms and custom modules. It also includes a flexible configuration system for hyperparameter tuning, logging utilities for experiment tracking, and compatibility with OpenAI Gym environments for seamless portability. Users can collaborate on shared environments and replay logged sessions for analysis.

The Berkeley Pacman Projects repository offers a modular Python codebase where users build and test AI agents in a Pacman maze. It guides learners through uninformed and informed search (DFS, BFS, A*), adversarial multi-agent search (minimax, alpha-beta pruning), and reinforcement learning (Q-learning with feature extraction). Integrated graphical interfaces visualize agent behavior in real time, while built-in test cases and an autograder verify correctness. By iterating on algorithm implementations, users gain practical experience in state space exploration, heuristic design, adversarial reasoning, and reward-based learning within a unified game framework.