Lizhi-sjtu/MARL-code-pytorch
PyTorch implementation of multi-agent reinforcement learning algorithms for cooperative and competitive agent environments.
Not currently ranked — collecting fresh signals.
star history
This repository provides concise PyTorch implementations of major multi-agent reinforcement learning (MARL) algorithms including MAPPO, MADDPG, MATD3, QMIX, and VDN. The implementations are designed to work with benchmark environments like the Multi-Agent Particle-World Environment (MPE) and StarCraft Multi-Agent Challenge (SMAC). The code supports both discrete and continuous action spaces, with modifications to the MPE source code to facilitate easy switching between action space types.
Frequently asked
- What is Lizhi-sjtu/MARL-code-pytorch?
- PyTorch implementation of multi-agent reinforcement learning algorithms for cooperative and competitive agent environments.
- Is MARL-code-pytorch open source?
- Yes — Lizhi-sjtu/MARL-code-pytorch is open source, released under the MIT license.
- What language is MARL-code-pytorch written in?
- Lizhi-sjtu/MARL-code-pytorch is primarily written in Python.
- How popular is MARL-code-pytorch?
- Lizhi-sjtu/MARL-code-pytorch has 739 stars on GitHub.
- Where can I find MARL-code-pytorch?
- Lizhi-sjtu/MARL-code-pytorch is on GitHub at https://github.com/Lizhi-sjtu/MARL-code-pytorch.