We consider learning a probabilistic classifier from partially-labelled
...
Noting that lemmas are a key feature of mathematics, we engage in an
inv...
Currently, the dominant paradigm in AI safety is alignment with human va...
Our paper explores the game theoretic value of the 7-in-a-row game. We r...
In this work we study how to learn good algorithms for selecting reasoni...
The Lottery Ticket Hypothesis postulates that a freshly initialized neur...
We present a reinforcement learning toolkit for experiments with guiding...
We present a reinforcement learning (RL) based guidance system for autom...
Regularizing the gradient norm of the output of a neural network with re...