Claude Formanek
Claude Formanek
### Feature Add support to run Mava systems as a single process program rather than a distributed program using Launchpad. It is very hard to debug Mava systems because of...
### Question **TL;DR: do you have baselines for performance on the environments using some popular MARL algorithm, say MADDPG or other?** Hi there, first of all, thanks for maintaining MAMuJoCo....
Many of the environments and datasets from the original OG-MARL release have not been added to the new experiment launcher yet. We are working on adding them as soon as...
After modifying the environment API used in OG-MARL, the old offline experience logger does not work anymore. We need to modify it to work with the new environment API. The...
I noticed you are using non-default SMAC arguments when initialising the environment. Can you explain why? And maybe provide a list of arguments you changed? Did you also change the...
Inspecting the datasets for 2x4 Ant I notice that the observation dimension for each agent is 113. But the observation dim when `agent_obsk=1` is supposed to be 52. Does that...
Currently, we only have Replay datasets on Gymnasium MAMuJoCo tasks. It would be nice to add Good, Medium and Poor ones.
PyTorch is most widely used by other researchers in the Offline MARL field. Adding PyTorch implementations for some of the baselines should improve the adoption of the baselines. ## High...