Results 181 to 190 of about 1,249,172 (345)

DAPPER: Discriminability-Aware Policy-to-Policy Preference-Based Reinforcement Learning for Query-Efficient Robot Skill Acquisition [PDF]

open access: yesarXiv
Preference-based Reinforcement Learning (PbRL) enables policy learning through simple queries comparing trajectories from a single policy. While human responses to these queries make it possible to learn policies aligned with human preferences, PbRL suffers from low query efficiency, as policy bias limits trajectory diversity and reduces the number of ...
arxiv  

De Novo Reconstruction of 3D Human Facial Images from DNA Sequence

open access: yesAdvanced Science, EarlyView.
This study introduces Difface, a novel deep‐learning model for reconstructing 3D facial images only from DNA data. By integrating transformer networks, spiral convolutions, and a diffusion model, Difface directly aligns high‐dimensional SNP data with 3D facial structures.
Mingqi Jiao   +11 more
wiley   +1 more source

Discriminating to learn to discriminate

open access: yes, 1997
Experiments in which subjects play simultaneously several finite prisoner's dilemma supergames reveal that many hypotheses used in the literature to explain cooperation are wrong. In particular the existence of player types is rejected as well as over-simplified behavioural postulates which allow for the existence of agents who make consistent errors ...
openaire   +1 more source

Listerin Alleviates Alzheimer's Disease through IRE1‐mediated Decay of TLR4 mRNA

open access: yesAdvanced Science, EarlyView.
Alzheimer's disease (AD) progression is influenced by microglia‐mediated neuroinflammation. Here, it is demonstrated that Listerin suppresses neuroinflammatory signaling and cognitive impairment in AD models by triggering IRE1α‐mediated TLR4 mRNA decay. Adenoviral Listerin delivery reduces amyloid‐β pathology, positioning it as a new therapeutic target.
Fei Qin   +9 more
wiley   +1 more source

An Aerial–Aquatic Hitchhiking Robot with Remora‐Inspired Tactile Sensors and Thrust Vectoring Units

open access: yesAdvanced Intelligent Systems, EarlyView., 2023
An untethered aerial–aquatic hitchhiking robot that can be remotely controlled for flying, swimming, and transiting air–water boundaries rapidly (0.16 s), is presented. Notably, it can autonomously attach to various surfaces in both air and water environments using a remora‐inspired suction disc with flexible tactile sensors.
Lei Li   +12 more
wiley   +1 more source

Home - About - Disclaimer - Privacy