Goto

Collaborating Authors

 latexit sha1


Learning Distributedand Fair Policiesfor Network Load Balancingas Markov Potential Game

Neural Information Processing Systems

At t 2 H inahorizonH ofthegireceiwi(t) 2 W, theworkload policy i 2 , where istheload t, a anactionai(t)= {aij(t)}Nj=1, accordingwi(t) are i(t). Q (o, a) r(o, a) Eo0[V (o0)] 2 , whereV (o0)= Ea0[Q (o0,a0) log (a0|o0)] and Q isthetargetQ network; theactorpolicy isupdatedwiththegradient r Eo[Ea [ log (a|o) Q (o, a)]].






Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio

Neural Information Processing Systems

The system consumes, as input, audio signals from headset microphones and body pose, and produces, as output, a 3D sound field surrounding the transmitter's