You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We extend pymarl2 to pymarl3, equipping the MARL algorithms with permutation invariance and permutation equivariance properties. The enhanced algorithm achieves 100% win rates on SMAC-V1 and superior performance on SMAC-V2.
A machine learning project utilizing a 1D CNN to simultaneously locate up to three acoustic sources. Features advanced signal processing techniques like Permutation Invariant Training (PIT) to stabilize learning, alongside a detailed analysis of how sampling rates and volume affect accuracy.