BenchMARL
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.
facebookresearch/BenchMARL
View on GitHub ↗BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically grounded in its two core tenets: reproducibility and standardization.
BenchMARL grew +1.5% in the last 30 days, ranks 21st of 74 in RL Environments, last commit 259 days ago.
Star trajectory
115 days tracked+1.5% in 30d, above the RL Environments median of +0.2%.
Last commit 259 days ago, staler than the median of 171d.
How it compares in RL Environments
Ranked 21st of 74 by stars.
- Language
- Python
- License
- MIT License
- Contributors
- 8
- Forks
- 142
- Watchers
- 12
- Open issues
- 30
- Releases
- 13
- Created
- 2023-08-22
- Stars this week
- +1
You've seen where BenchMARL stands today.
Get the moves before everyone else: the 5 RL Environments repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.