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.

Multiagent-Prediction-Reward is a research-oriented framework that integrates prediction models and reward distribution mechanisms for multi-agent reinforcement learning. It includes environment wrappers, neural modules for forecasting peer actions, and customizable reward routing logic that adapts to agent performance. The repository provides configuration files, example scripts, and evaluation dashboards to run experiments on cooperative tasks. Users can extend the code to test novel reward functions, integrate new environments, and benchmark against established multi-agent RL algorithms.