multi_agent_celar is designed as a modular AI platform enabling emergent-language communication among multiple intelligent agents in simulated environments. Users can define agent behaviors via policy files, configure environment parameters, and launch coordinated training sessions where agents evolve their own communication protocols to solve cooperative tasks. The framework includes evaluation scripts, visualization tools, and support for scalable experiments, making it ideal for research on multi-agent collaboration, emergent language, and decision-making processes.

This repository provides an end-to-end reinforcement learning framework for StarCraft II gameplay research. The core agent uses Proximal Policy Optimization (PPO) to learn policy networks that interpret observation data from the PySC2 environment and output precise in-game actions. Developers can configure neural network layers, reward shaping, and training schedules to optimize performance. The system supports multiprocessing for efficient sample collection, logging utilities for monitoring training curves, and evaluation scripts for running trained policies against scripted or built-in AI opponents. The codebase is written in Python and leverages TensorFlow for model definition and optimization. Users can extend components such as custom reward functions, state preprocessing, or network architectures to suit specific research objectives.