PapeRman #8

A Baseline for Any Order Gradient Estimation in Stochastic Computation GraphsAuthors: Jingkai Mao, Jakob Foerster, Tim Rocktaschel, Maruan Al-Shedivat 4 Gregory Farquhar, Shimon WhitesonAbstract: 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 that arise in, e.g., multi-agent reinforcement learning … Continue reading PapeRman #8

PapeRman #7

HOList: An Environment for Machine Learning of Higher-Order Theorem Proving link: Abstract We present an environment, benchmark, and deep learning driven automated theorem prover for higher-order logic. Higher-order interactive theorem provers enable the formalization of arbitrary mathematical theories and thereby present an interesting, open-ended challenge for deep learning. We provide an open-source framework based … Continue reading PapeRman #7