Constructing agents with planning capabilities has long been one of the main challenges in
the pursuit of artificial intelligence. Tree-based planning methods have enjoyed huge …

Precise timekeeping is critical to metrology, forming the basis by which standards of time,
length, and fundamental constants are determined. Stable clocks are particularly valuable in …

We present a method for using previously-trained 'teacher' agents to kickstart the training of
a new 'student' agent. To this end, we leverage ideas from policy distillation and population …

The reinforcement learning (RL) community has made great strides in designing algorithms
capable of exceeding human performance on specific tasks. These algorithms are mostly …

We propose a novel policy update that combines regularized policy optimization with model
learning as an auxiliary loss. The update (henceforth Muesli) matches MuZero’s state-of-the-…

Qudi is a general, modular, multi-operating system suite written in Python 3 for controlling
laboratory experiments. It provides a structured environment by separating functionality into …

Many important real-world problems have action spaces that are high-dimensional, continuous
or both, making full enumeration of all possible actions infeasible. Instead, only small …

Childhood maltreatment (CM) is a risk factor for numerous mental disorders. However, the
specificity of CM types in mental disorders is still being discussed. The present study …

Major depressive disorder (MDD), bipolar disorder (BD), and schizophrenia spectrum disorder
(SSD, schizophrenia, and schizoaffective disorder) overlap in symptomatology, risk factors…

Objective To examine attachment insecurity and low social support as potential mediators of
the association between childhood maltreatment (CM) types and depression severity in …