Simple artificial-intelligence problem puts researchers up against a logical paradox discovered by famed mathematician Kurt Gödel. — Read on http://www.nature.com/articles/d41586-019-00083-3

# Category: Machine Learning

## What-IF tool

What If… you could inspect a machine learning model, with no coding required? https://pair-code.github.io/what-if-tool/index.html#demos

## A quantum-inspired classical algorithm for recommendation systems

This preprint shows that Kerenidis and Prakash’s quantum machine learning (QML) algorithm, one of the strongest candidates for provably exponential speedups in QML, does not in fact give an exponential speedup over classical algorithms. https://arxiv.org/pdf/1807.04271.pdf

## Variational Option Discovery Algorithms

Paper Abstract: “We explore methods for option discovery based on variational inference and make two algorithmic contributions. First: we highlight a tight connection between variational option discovery methods and variational autoencoders, and introduce Variational Autoencoding Learning of Options by Reinforcement (VALOR), a new method derived from the connection. In VALOR, the policy encodes contexts from…

## What’s New in Deep Learning Research: Reinforcement Learning with Infinite Agents Using Mean Field Games

towardsdatascience.com/whats-new-in-deep-learning-research-reinforcement-learning-with-infinite-agents-using-mean-field-65044838905d

## A differetiable Dynamic Programming

Differentiable Dynamic Programming for Structured Prediction and Attention

## Hallucinogenic Deep Reinforcement Learning

Teaching a machine to master car racing and fireball avoidance through “World Models”