Online platforms employ recommendation systems to enhance customer engag...
In response to the global challenge of mental health problems, we propos...
Recent advances in large language models (LLMs) have led to the developm...
We introduce a Reinforcement Learning Psychotherapy AI Companion that
ge...
We present the TherapyView, a demonstration system to help therapists
vi...
The field of compositional generalization is currently experiencing a
re...
Multi-armed bandit (MAB) problems are mainly studied under two extreme
s...
As a predictive measure of the treatment outcome in psychotherapy, the
w...
In recent years, the Neurosymbolic framework has attracted a lot of atte...
This paper is concerned with online targeted advertising on social netwo...
In this work, we compare different neural topic modeling methods in lear...
The therapeutic working alliance is an important predictor of the outcom...
In light of the COVID-19 pandemic, it is an open challenge and critical
...
Reinforcement learning (RL) algorithms aim to learn optimal decisions in...
The Multi-armed bandit offer the advantage to learn and exploit the alre...
Unlike traditional time series, the action sequences of human decision m...
In this paper, we analyze and extend an online learning framework known ...
Model-agnostic meta-learning (MAML) effectively meta-learns an initializ...
Spectral clustering has shown a superior performance in analyzing the cl...
Dirichlet-multinomial (DMN) distribution is commonly used to model
over-...
We consider a novel variant of the contextual bandit problem (i.e., the
...
We consider a novel variant of the contextual bandit problem (i.e., the
...
The CASH problem has been widely studied in the context of automated
con...
Prisoner's Dilemma mainly treat the choice to cooperate or defect as an
...
Artificial behavioral agents are often evaluated based on their consiste...
We study here the problem of learning the exploration exploitation trade...
Data science is labor-intensive and human experts are scarce but heavily...
Drawing an inspiration from behavioral studies of human decision making,...
Drawing an inspiration from behavioral studies of human decision making,...
We study the automated machine learning (AutoML) problem of jointly sele...
Autonomous cyber-physical agents and systems play an increasingly large ...
AI systems that learn through reward feedback about the actions they tak...
We propose a novel online algorithm for training deep feedforward neural...
We consider an extension of the contextual bandit setting, motivated by
...
Given the recent success of Deep Learning applied to a variety of single...
Drawing an inspiration from behavioral studies of human decision making,...
We consider a novel formulation of the multi-armed bandit model, which w...
Active learning strategies respond to the costly labelling task in a
sup...
We introduce in this paper an algorithm named Contextuel-E-Greedy that
t...
We present Exponentiated Gradient LINUCB, an algorithm for con-textual
m...
Ubiquitous information access becomes more and more important nowadays a...