PyMARLzoo+ — Extended MARL benchmarking with 16 algorithms and broad environment support
1.3K
PyMARLzoo+ is an extended benchmarking suite for fully cooperative multi-agent reinforcement learning, building on EPyMARL. It adds seven state-of-the-art algorithms (HAPPO, MAT-DEC, QPLEX, EOI, EMC, MASER and CDS) to the nine already supported, and integrates seamlessly with a wide range of PettingZoo and Gymnasium environments—including Overcooked, Capture Target, Box Pushing, RWARE, LBF and more—so you can train and evaluate complex cooperative tasks out of the box .
1.Pull the image
docker pull aillabdsunipi/pymarlzooplus:latest
2.Mount your working directory
Keep your configs and code outside the container:
docker run -it --rm \
-v /path/to/your/project:/workspace \
aillabdsunipi/pymarlzooplus:latest /bin/bash
Content type
Image
Digest
sha256:9b6fd282f…
Size
6.4 GB
Last updated
7 months ago
docker pull ailabdsunipi/pymarlzooplus