problem for evaluating mamujoco

[Lin-c-x]

i can run the code to train mamujoco,but when i evaluate it , it occurs some problems

[zbzhu99]

Sorry for the late reply. Could you share the result of executing pip list in the Python environment you're using?

[Lin-c-x]

absl-py 2.1.0 aiofile 3.8.8 aiofiles 23.2.1 argcomplete 3.2.2 astunparse 1.6.3 atomicwrites 1.4.1 attrs 23.2.0 black 23.1.0 boto3 1.34.55 botocore 1.34.55 bracex 2.4 cachetools 4.2.4 caio 0.9.13 certifi 2024.2.2 cffi 1.16.0 charset-normalizer 3.3.2 click 8.1.7 cloudpickle 1.3.0 contourpy 1.1.1 cycler 0.12.1 Cython 0.29.28 D4RL 1.1 ddpg-agent 0.0.1 /data/lcx/madiff/third_party/ddpg-agent deepdiff 6.7.1 diffusers 0.24.0 dill 0.3.8 dm-control 1.0.8 dm-env 1.6 dm-tree 0.1.8 einops 0.7.0 enum34 1.1.10 expandvars 0.12.0 fasteners 0.19 filelock 3.13.1 flatbuffers 23.5.26 fonttools 4.49.0 fsspec 2024.2.0 functional-notations 0.5.2 future 1.0.0 gast 0.4.0 gitdb 4.0.5 GitPython 3.1.9 glfw 2.7.0 google-auth 2.28.1 google-auth-oauthlib 1.0.0 google-pasta 0.2.0 graphviz 0.20.1 grpcio 1.62.0 gtimer 1.0.0b5 gym 0.10.8 gym-notices 0.0.8 gymnasium 0.27.1 gymnasium-notices 0.0.1 h5py 3.10.0 html5tagger 1.3.0 httptools 0.6.1 huggingface-hub 0.21.3 idna 3.6 imageio 2.34.0 imageio-ffmpeg 0.4.9 importlib-metadata 7.0.1 isort 5.12.0 jax-jumpy 1.0.0 jaynes 0.8.11 Jinja2 3.1.3 jmespath 1.0.1 joblib 0.16.0 keras 2.13.1 kiwisolver 1.4.5 labmaze 1.0.6 libclang 16.0.6 lxml 5.1.0 madiff 0.0.0 /data/lcx/madiff MAMujoco 1.1.0 Markdown 3.5.2 MarkupSafe 2.1.5 matplotlib 3.6.3 mjrl 1.0.0 ml-logger 0.8.69 mock 5.1.0 more-itertools 10.2.0 mpyq 0.2.5 mujoco 2.3.0 mujoco-py 2.1.2.14 multiagent 0.0.1 /data/lcx/madiff/third_party/multiagent-particle-envs multidict 6.0.5 mypy-extensions 1.0.0 networkx 3.1 numpy 1.24.3 numpy-stl 2.17.1 oauthlib 3.2.2 OG-MARL 0.0.1 /data/lcx/madiff/third_party/og-marl opencv-python 4.9.0.80 opt-einsum 3.1.0 ordered-set 4.1.0 packaging 23.0 pandas 1.3.5 params-proto 2.9.6 path 15.0.0 pathspec 0.12.1 pillow 10.2.0 pip 23.3.1 platformdirs 4.2.0 pluggy 1.4.0 portpicker 1.6.0 protobuf 3.20.3 psutil 5.9.8 py 1.11.0 pyasn1 0.5.1 pyasn1-modules 0.3.0 pybullet 3.2.6 pycparser 2.21 pycurl 7.45.3 pygame 2.5.2 pyglet 1.5.0 PyOpenGL 3.1.5 pyparsing 2.2.2 pyrsistent 0.16.0 PySC2 3.0.0 pytest 3.8.2 python-dateutil 2.7.3 python-utils 2.4.0 pytz 2024.1 PyWavelets 1.4.1 PyYAML 6.0 regex 2023.12.25 requests 2.31.0 requests-futures 1.0.1 requests-oauthlib 1.3.1 requests-toolbelt 1.0.0 rsa 4.9 ruamel.yaml 0.18.6 ruamel.yaml.clib 0.2.8 s2clientprotocol 5.0.12.91115.0 s2protocol 5.0.12.91115.0 s3transfer 0.10.0 safetensors 0.4.2 sanic 23.12.1 Sanic-Cors 2.2.0 sanic-routing 23.12.0 scikit-image 0.19.3 scikit-video 1.1.11 scipy 1.10.1 seaborn 0.13.2 setuptools 68.2.2 six 1.16.0 sk-video 1.1.10 SMAC 1.0.0 smmap 3.0.5 subprocess32 3.5.4 tensorboard 2.13.0 tensorboard-data-server 0.7.2 tensorboardX 2.0 tensorflow 2.13.1 tensorflow-estimator 2.13.0 tensorflow-io-gcs-filesystem 0.34.0 termcolor 2.4.0 tifffile 2023.7.10 tomli 2.0.1 torch 1.12.1+cu113 torchviz 0.0.2 tqdm 4.66.2 tracerite 1.1.1 typed-argument-parser 1.7.2 typing_extensions 4.5.0 typing-inspect 0.9.0 ujson 5.9.0 urllib3 1.26.18 uvloop 0.19.0 waterbear 2.6.8 wcmatch 8.5.1 websocket-client 1.7.0 websockets 12.0 Werkzeug 3.0.1 wheel 0.41.2 whichcraft 0.6.1 wrapt 1.16.0 zipp 3.17.0

[Lin-c-x]

And when I run spread of the mpe environment, the result is above 500. Is there anythig need to change? I try to change the return_scale, but seems useless.

[zbzhu99]

Please try installing the local multiagent mujoco environment with:

pip install -e ./third_party/multiagent_mujoco

[zbzhu99]

And when I run spread of the mpe environment, the result is above 500. Is there anythig need to change? I try to change the return_scale, but seems useless.

To be consistent with the results in the OMAR paper, we reported normalized scores on MPE. Details on normalization can be seen in Appendix E.1 of our arXiv paper.

[Lin-c-x]

thank you for your reply