search

FLAIROx / JaxMARL

Multi-Agent Reinforcement Learning with JAX
Apache License 2.0
414 stars 72 forks source link

TransfQMix release #58

Closed mttga closed 8 months ago

mttga commented 8 months ago

Here are the results average across 4 seeds:

Results are better than QMix for most of the maps with except of 3s5z and 3s5z_vs_3s_6z. But the main advantage of transformers is the potential transferability of the agent parameters and the learned qmix function between scenarios.

amacrutherford commented 8 months ago

Here are the results average across 4 seeds:

* test won: https://api.wandb.ai/links/mttga/2beham1m

* test returns: https://api.wandb.ai/links/mttga/6yszv25o

Results are better than QMix for most of the maps with except of 3s5z and 3s5z_vs_3s_6z. But the main advantage of transformers is the potential transferability of the agent parameters and the learned qmix function between scenarios.

awesome!