Results 141 to 150 of about 6,522,305 (296)

Graph Neural Network‐Based Reinforcement Learning for Decentralized Multi‐Robot Manipulation

Advanced Intelligent Systems, EarlyView.
Robot arms lifting a large object face a trade‐off: centralized controllers explode in parameters, while decentralized ones cannot coordinate. A GNN resolves this—each arm runs its own network but acts on the full team state, achieving centralized‐level coordination with decentralized execution. Trained across team sizes, a single policy scales to four‐
Tong Chen, Bo Fu, Dawn Tilbury, Kira Barton   +3 more
wiley   +1 more source

Reinforcement learning for medical image analysis: a systematic review of algorithms, engineering challenges, and clinical deployment

Computer Assisted Surgery
Reinforcement learning (RL) has emerged as a powerful artificial intelligence paradigm in medical image analysis, excelling in complex decision-making tasks.
Masuda Begum Sampa, Nor Hidayati Abdul Aziz, Md. Siddikur Rahman, Nor Azlina Ab. Aziz, Rosli Besar, Anith Khairunnisa Ghazali   +5 more
doaj   +1 more source

RL as Regressor: A Reinforcement Learning Approach for Function Approximation

CoRR
Standard regression techniques, while powerful, are often constrained by predefined, differentiable loss functions such as mean squared error. These functions may not fully capture the desired behavior of a system, especially when dealing with asymmetric costs or complex, non-differentiable objectives. In this paper, we explore an alternative paradigm:
openaire   +4 more sources

RL-X: A Deep Reinforcement Learning Library (Not Only) for RoboCup

This paper presents the new Deep Reinforcement Learning (DRL) library RL-X and its application to the RoboCup Soccer Simulation 3D League and classic DRL benchmarks. RL-X provides a flexible and easy-to-extend codebase with self-contained single directory algorithms.
Nico Bohlinger, Klaus Dorer
openaire   +4 more sources

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

CoRR
Vision-Language-Action (VLA) models have recently emerged as a powerful paradigm for robotic manipulation. Despite substantial progress enabled by large-scale pretraining and supervised fine-tuning (SFT), these models face two fundamental challenges: (i) the scarcity and high cost of large-scale human-operated robotic trajectories required for SFT ...
Haozhan Li, Yuxin Zuo, Jiale Yu, Yuhao Zhang, Zhaohui Yang, Kaiyan Zhang, Xuekai Zhu, Yuchen Zhang, Tianxing Chen, Ganqu Cui, Dehui Wang, Dingxiang Luo, Yuchen Fan, Youbang Sun, Jia Zeng, Jiangmiao Pang, Shanghang Zhang, Yu Wang 0002, Yao Mu 0001, Bowen Zhou 0002, Ning Ding 0002   +20 more
openaire   +3 more sources

From Instruction to Inheritance: Scaling Robot Learning Through Knowledge Circulation

Advanced Intelligent Systems, EarlyView.
Robot learning moves from one‐way instruction toward knowledge circulation. Humans teach robots, robots teach one another, and robots share acquired skills with humans. This perspective connects teaching, embodiment, and learning architectures to explore how knowledge is inherited, adapted, and enriched across agents, opening a path toward scalable ...
Kento Kawaharazuka, Shunki Itadera, Kohei Honda, Takato Horii, Asako Kanezaki, Taisuke Kobayashi, Kenji Koide, Shuhei Kurita, Koshi Makihara, Kazuki Miyazawa, Masaki Murooka, Yuki Onishi, Satoshi Yagi, Satoshi Yamamori   +13 more
wiley   +1 more source

Hippocampal Seizure‐Related Burden is Associated with Accelerated Long‐Term Forgetting in Focal Epilepsy

Annals of Neurology, EarlyView.
Objective Memory impairment is a frequent comorbidity of focal epilepsy, incompletely explained by seizure frequency or structural pathology. Ictal and postictal hippocampal dysfunction disrupt memory processes, but their cumulative impact remains poorly quantified.
Ionuț‐Flavius Bratu, Isabelle Lambert, Olivier Felician, Samuel Medina Villalon, Agnès Trébuchon, Fabrice Bartolomei   +5 more
wiley   +1 more source

Comparative analysis of cytoarchitectonic and neurochemical aspects of the globus pallidus in the rock cavy (Kerodon rupestris) and the common marmoset (Callithrix jacchus)

The Anatomical Record, EarlyView.
Abstract The globus pallidus (GP), a subcortical structure within the basal ganglia, plays a crucial role in modulating cortico‐subcortical circuits related to motor control and associative/limbic functions. However, the cytoarchitectonic and neurochemical organization of this structure remains poorly characterized in naturally existing wild‐type ...
Lavínnya Yáskara de Aquino Matoso, Yasmin Pinto Fernandes Albuquerque, Karina Maia Paiva, Rodrigo Freire Oliveira, Nelyane Nayara Martins de Santana, Expedito Silva do Nascimento‐Júnior, Rovena Clara G. J. Engelberth, Jeferson de Souza Cavalcante, Adhil Bhagwandin, Paulo Leonardo Araújo de Góis Morais, José Rodolfo Lopes de Paiva Cavalcanti   +10 more
wiley   +1 more source

Hybrid Distributed and Decentralised Reinforcement Learning for Formation Control of Multi‐Robots With Obstacle Avoidance

CAAI Transactions on Intelligence Technology
Recently, learning‐based control for multi‐robot systems (MRS) with obstacle avoidance has received increasing attention. The goals of formation control and obstacle avoidance could be intrinsically tied.
Yaoqian Peng, Xinglong Zhang, Haibin Xie, Xin Xu   +3 more
doaj   +1 more source

Using Reinforcement Learning to Develop a Novel Gait for a Bio-Robotic California Sea Lion

Biomimetics
While researchers have made notable progress in bio-inspired swimming robot development, a persistent challenge lies in creating propulsive gaits tailored to these robotic systems.
Anthony Drago, Shraman Kadapa, Nicholas Marcouiller, Harry G. Kwatny, James L. Tangorra   +4 more
doaj   +1 more source