Gradient surgery for multi-task learning
While deep learning and deep reinforcement learning (RL) systems have demonstrated
impressive results in domains such as image classification, game playing, and robotic control, …
impressive results in domains such as image classification, game playing, and robotic control, …
Diversity is all you need: Learning skills without a reward function
Intelligent creatures can explore their environments and learn useful skills without supervision.
In this paper, we propose DIAYN ('Diversity is All You Need'), a method for learning useful …
In this paper, we propose DIAYN ('Diversity is All You Need'), a method for learning useful …
Multifactorial evolution: Toward evolutionary multitasking
The design of evolutionary algorithms has typically been focused on efficiently solving a single
optimization problem at a time. Despite the implicit parallelism of population-based search…
optimization problem at a time. Despite the implicit parallelism of population-based search…
Soft actor-critic algorithms and applications
Model-free deep reinforcement learning (RL) algorithms have been successfully applied to
a range of challenging sequential decision making and control tasks. However, these …
a range of challenging sequential decision making and control tasks. However, these …
Craniofacial and upper airway morphology in adult obstructive sleep apnea patients: a systematic review and meta-analysis of cephalometric studies
Obstructive sleep apnea (OSA) is one of the common sleep breathing disorders in adults,
characterised by frequent episodes of upper airway collapse during sleep. Craniofacial …
characterised by frequent episodes of upper airway collapse during sleep. Craniofacial …
Synthesis of silver nanoparticles using curcumin-cyclodextrins loaded into bacterial cellulose-based hydrogels for wound dressing applications
Chronic wounds are often recalcitrant to treatment because of high microbial bioburden and
the problem of microbial resistance. Silver is a broad-spectrum natural antimicrobial agent …
the problem of microbial resistance. Silver is a broad-spectrum natural antimicrobial agent …
Learning complex dexterous manipulation with deep reinforcement learning and demonstrations
Dexterous multi-fingered hands are extremely versatile and provide a generic way to perform
a multitude of tasks in human-centric environments. However, effectively controlling them …
a multitude of tasks in human-centric environments. However, effectively controlling them …
Phytochemistry of medicinal plants
Medicinal plants are a rich source of bioactive phytochemicals or bionutrients. Studies
carried out during the past 2–3 decades have shown that these phytochemicals have an …
carried out during the past 2–3 decades have shown that these phytochemicals have an …
Modeling and analyzing millimeter wave cellular systems
We provide a comprehensive overview of mathematical models and analytical techniques
for millimeter wave (mmWave) cellular systems. The two fundamental physical differences …
for millimeter wave (mmWave) cellular systems. The two fundamental physical differences …
Awac: Accelerating online reinforcement learning with offline datasets
Reinforcement learning (RL) provides an appealing formalism for learning control policies
from experience. However, the classic active formulation of RL necessitates a lengthy active …
from experience. However, the classic active formulation of RL necessitates a lengthy active …