Downloads · 30 days
7
13% of all-time downloads
epymarl-mappo-smacv2-protoss-5-vs-5
Tasha02/epymarl-mappo-smacv2-protoss-5-vs-5
epymarl-mappo-smacv2-protoss-5-vs-5 is a machine learning model from Tasha02. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for epymarl. The card lists the license as apache-2.0.
Multi-Agent PPO (MAPPO) agents trained with EPyMARL on the SMACv2 protoss5vs5 scenario (StarCraft II).
All-time downloads
54
Public
Repo size
3.6 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.th1.8 MB · 100%
At a glance
- Library
- epymarl
- License
- apache-2.0
- Access
- Public
- Created
- Jun 18, 2026
- Updated
- Jun 19, 2026
- SHA
- 5101b919
Model card
From the Hugging Face model README
MAPPO on SMACv2 protoss_5_vs_5
Multi-Agent PPO (MAPPO) agents trained with EPyMARL
on the SMACv2 protoss_5_vs_5 scenario (StarCraft II).
- Algorithm: MAPPO (shared parameters, RNN policy, centralised value function)
- Environment: SMACv2
protoss_5_vs_5 - Checkpoint step: 10051667 environment timesteps
- Greedy test win rate at upload: ~0.50 greedy (converged, 10M steps; peak 0.54-0.65)
Files
agent.th— actor network weightscritic.th— centralised critic weights*_opt.th— optimiser statesconfig.json— full training configuration
Usage
Load into EPyMARL by pointing checkpoint_path at a directory containing a
10051667/ subfolder with these files:
python src/main.py --config=mappo --env-config=sc2v2 \
with env_args.map_name=protoss_5_vs_5 checkpoint_path=<dir> evaluate=True render=False
- Library
- epymarl
- License
- apache-2.0
- Created
- Jun 18, 2026
- Updated
- Jun 19, 2026