# MADDPG_Multi_UAV_Roundup

**Repository Path**: networkscontrol/MADDPG_Multi_UAV_Roundup

## Basic Information

- **Project Name**: MADDPG_Multi_UAV_Roundup
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2024-10-21
- **Last Updated**: 2025-01-09

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

## Key dependencies based (Lower versions are not guaranteed to be feasible):

python: 3.9.0

numpy: 1.26.0

gym: 0.26.2

pillow: 10.2.0

torch: 2.4.0+cu124

torchaudio: 2.4.0+cu124

torchvision: 0.19.0+cu124

## Explanation of Document

- `agent`/`buffer`/`maddpg`/`networks`: Refer to Phil's work -> [PhilMADDPG](https://github.com/philtabor/Multi-Agent-Reinforcement-Learning);

- `sim_env`: Customized Multi-UAV round-up environment;

- `main`: Main loop to train agents;

- `main_evaluate`: Only rendering part is retained in `main`, in order to evaluate models (a set of feasible models is provided in `tmp/maddpg/UAV_Round_up`;

- `math_tool`: some math-relevent functions.

<img title="" src="Roundup.png" alt="" data-align="center" width="470">