A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs

Jingkai Mao, Jakob N. Foerster, Tim Rocktäschel, Maruan Al-Shedivat, Gregory Farquhar, Shimon Whiteson

Abstract: By enabling correct differentiation in Stochastic Computation Graphs (SCGs), the infinitely differentiable Monte-Carlo estimator (DiCE) can generate correct estimates for the higher order gradients...