A variety of methods have been applied to the architectural configuration and learning or
training of artificial deep neural networks (DNN). These methods play a crucial role in the …

The scope of human learning and development poses a radical challenge for cognitive
science. We propose that developmental theories can address this challenge by adopting …

Reinforcement learning promises to solve complex sequential-decision problems
autonomously by specifying a high-level reward function only. However, reinforcement …

In recent years, the research community has witnessed an explosion of literature dealing
with the mimicking of behavioral patterns and social phenomena observed in nature towards …

We introduce a new unsupervised pretraining objective for reinforcement learning. During
the unsupervised reward-free pretraining phase, the agent maximizes mutual information …

A grand challenge in reinforcement learning is intelligent exploration, especially when
rewards are sparse or deceptive. Two Atari games serve as benchmarks for such hard …

The original" Seven Motifs" set forth a roadmap of essential methods for the field of scientific
computing, where a motif is an algorithmic method that captures a pattern of computation …

Evolution strategies (ES) are a family of black-box optimization algorithms able to train deep
neural networks roughly as well as Q-learning and policy gradient methods on challenging …

Many fields use search algorithms, which automatically explore a search space to find high-
performing solutions: chemists search through the space of molecules to discover new …

While the history of machine learning so far largely encompasses a series of problems
posed by researchers and algorithms that learn their solutions, an important question is …