MCTF Software Setup and Installation

MCTF uses the Pyquaticus game simulation environment. Pyquaticus is an open-source, Python-based library developed at MIT-Lincoln Labs that enables multi-agent training via reinforcement learning (RL) using a Petting Zoo/Gymnasium environment. It supports the RL-Lib deep RL library and can be also integrated with other deep RL libraries like Stable-Baselines and user-defined RL algorithm implementations in Python. Pyquaticus can also support heuristics-based agents for controlling players’ actions as well as keyboard control of the agents' movements.

Installation and Training Your First Agents

Steps to Download and Install Pyquaticus

1. Download Pyquaticus here.
2. Follow the instructions in the README.md file inside the downloaded repository.
3. Setup a python virtual environment using one of the methods given below.
4. Train RL agents to play MCTF using the Getting Started with Pyquaticus instructions and sample code here.

Setting up a Python Virtual Environment

1. Install Miniconda here.
2. Navigate into the git repository in the terminal.
3. Run './setup-conda-env.sh light' (Light installs just the environment) or './setup-conda-env.sh full' (Recommended, includes rllib for Deep Reinforcement Learning)

1. Download and install Python 3.10
2. In a terminal run python3.10 -m venv <name>
3. Run './setup-conda-env.sh light' (Light installs just the environment) or './setup-conda-env.sh full' (Recommended, includes rllib for Deep Reinforcement Learning)

Setting Up On Windows

1. Install Miniconda here.
2. Clone Pyquaticus Github Repository.
3. Navigate into the git repository in the terminal.
4. Remove Line: 56 (pymoos==2022.1) from pyproject.toml
5. Run './setup-conda-env.sh light' [ if using wsl ] (Light installs just the environment) or './setup-conda-env.sh full' (Recommended, includes rllib for Deep Reinforcement Learning)
6. Or run "pip install -e .[torch,ray]"" (full) "pip install -e ." (light)