Closed amacrutherford closed 5 months ago
I've seen you reduced the number of envs for smax. How long does it take to train now? Nice to see good performances on MPE btw, it makes sense to increase the total timesteps there for IPPO. I think original MAPPO paper reports results on 2e7 on this env
I've seen you reduced the number of envs for smax. How long does it take to train now? Nice to see good performances on MPE btw, it makes sense to increase the total timesteps there for IPPO. I think original MAPPO paper reports results on 2e7 on this env
ah yep will put that back up to 128, was at 16 for comparisons to mava as they use 16 envs across 8 workers. Yes it is! Ah cool will increase to that for the submission
SMAX & MPE results are good. Hanabi only good for IPPO, something weird going on with MAPPO.
SMAX results
These are over 10 seeds, max and min win rate shown with the shaded region.
![SMAX_smacv2_20_units](https://github.com/FLAIROx/JaxMARL/assets/66562395/c84b0aef-6709-4fd2-96f7-4c47bba24711)
MPE
Returns for MPE simple spread![mpe_simple_spread](https://github.com/FLAIROx/JaxMARL/assets/66562395/493d85ca-c8bd-458a-af14-aec2bfa77456)
hanabi
top lines are IPPO, bottom lines MAPPO. @mttga and I will take a look at the cause of this![hanabi](https://github.com/FLAIROx/JaxMARL/assets/66562395/4208073a-fdc8-4f85-95d0-478f2cfefd23)