oxwhirl/pymarl
A Python framework for deep multi-agent reinforcement learning implementing value decomposition algorithms for cooperative multi-agent control.
Not currently ranked — collecting fresh signals.
star history
PyMARL provides implementations of state-of-the-art multi-agent reinforcement learning algorithms including QMIX, COMA, VDN, IQL, and QTRAN. The framework is built on PyTorch and uses the SMAC environment (StarCraft II Multi-Agent Challenge) for evaluation. Researchers can run experiments by specifying algorithm and environment configurations, with results logged for analysis.
Frequently asked
- What is oxwhirl/pymarl?
- A Python framework for deep multi-agent reinforcement learning implementing value decomposition algorithms for cooperative multi-agent control.
- Is pymarl open source?
- Yes — oxwhirl/pymarl is open source, released under the Apache-2.0 license.
- What language is pymarl written in?
- oxwhirl/pymarl is primarily written in Python.
- How popular is pymarl?
- oxwhirl/pymarl has 2.2k stars on GitHub.
- Where can I find pymarl?
- oxwhirl/pymarl is on GitHub at https://github.com/oxwhirl/pymarl.