Results 61 to 70 of about 34,803,504 (287)

Weakly Supervised Reinforcement Learning for Autonomous Highway Driving via Virtual Safety Cages

Sensors, 2021
The use of neural networks and reinforcement learning has become increasingly popular in autonomous vehicle control. However, the opaqueness of the resulting control policies presents a significant barrier to deploying neural network-based control in ...
Sampo Kuutti, Richard Bowden, Saber Fallah   +2 more
doaj   +1 more source

Model-Based Reinforcement Learning With Isolated Imaginations

IEEE Transactions on Pattern Analysis and Machine Intelligence
World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios like autonomous driving, noncontrollable dynamics that are independent or sparsely dependent on action signals often exist, making it challenging to learn effective world models.
Minting Pan, Xiangming Zhu 0002, Yitao Zheng, Yunbo Wang, Xiaokang Yang 0001   +4 more
openaire   +5 more sources

Self‐Regulated Learning Meets AI: Reinterpreting Self‐Regulation, Co‐Regulation, and Socially Shared Regulation in Human–AI Interaction

New Directions for Adult and Continuing Education, EarlyView.
ABSTRACT Advancing artificial intelligence (AI) has transformed learning and work, yet higher education and professional development programs have not systematically equipped learners for AI‐prevalent environments. This lack of preparation creates uncertainty regarding control, responsibility, trust, and accountability.
Moon‐Heum Cho, Jerusalem Merkebu
wiley   +1 more source

A Reinforcement Learning Model Based on Temporal Difference Algorithm

IEEE Access, 2019
In some sense, computer game can be used as a test bed of artificial intelligence to develop intelligent algorithms. The paper proposed a kind of intelligent method: a reinforcement learning model based on temporal difference (TD) algorithm. And then the
Xiali Li, Zhengyu Lv, Song Wang, Zhi Wei, Licheng Wu   +4 more
doaj   +1 more source

Cyberspace attack and defense game based on reward randomization reinforcement learning

Array, 2022
The existing cyberspace attack and defense method can be regarded as game, but most of the game only involves network information, not include cyberspace's states, attacker's and defender's actions.
Lei Zhang, Hongmei Li, Yu Pan, Qibin Zheng, Wei Li, Yi Liu   +5 more
doaj   +1 more source

Model-Based Offline Quantum Reinforcement Learning

2024 IEEE International Conference on Quantum Computing and Engineering (QCE)
This paper presents the first algorithm for model-based offline quantum reinforcement learning and demonstrates its functionality on the cart-pole benchmark. The model and the policy to be optimized are each implemented as variational quantum circuits. The model is trained by gradient descent to fit a pre-recorded data set. The policy is optimized with
Simon Eisenmann, Daniel Hein 0001, Steffen Udluft, Thomas A. Runkler   +3 more
openaire   +2 more sources

RNA Sequencing Resolves Cryptic Pathogenic Variants in Mitochondrial Disease

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective Mitochondrial diseases are the most common inherited metabolic disorders, characterized by pronounced clinical and genetic heterogeneity that complicates molecular diagnosis. Although DNA‐based sequencing approaches have become standard in genetic testing, up to half of patients remain without a definitive diagnosis.
Zhimei Liu, Xin Duan, Fatemeh Peymani, Jia Wang, Chengjia Bao, Chaolong Xu, Ying Zou, Zixuan Zhang, Yunxi Zhang, Tongyue Li, Martin Pavlov, Junling Wang, Minhan Song, Tianyu Song, Xiaodi Han, Mingxi Sun, Danmin Shen, Ruoyu Duan, Huafang Jiang, Manting Xu, Holger Prokisch, Fang Fang   +21 more
wiley   +1 more source

DETEAMSK: A Model-Based Reinforcement Learning Approach to Intelligent Top-Level Planning and Decisions for Multi-Drone Ad Hoc Teamwork by Decoupling the Identification of Teammate and Task

Aerospace
The ability to collaborate with new teammates, adapt to unfamiliar environments, and engage in effective planning is essential for multi-drone agents within unmanned combat systems.
Penghui Xu, Yu Zhang, Le Hao, Qilin Yan
doaj   +1 more source

Deep Reinforcement Learning Portfolio Model Based on Dynamic Selectors [PDF]

Jisuanji kexue
In recent years,portfolio management problems have been extensively studied in the field of artificial intelligence,but there are some improvements in the existing quantitative trading methods based on deep learning.First of all,the prediction model of ...
ZHAO Miao, XIE Liang, LIN Wenjing, XU Haijiao
doaj   +1 more source

Transferring Instances for Model-Based Reinforcement Learning [PDF]

, 2008
Reinforcement learningagents typically require a significant amount of data before performing well on complex tasks. Transfer learningmethods have made progress reducing sample complexity, but they have primarily been applied to model-free learning methods, not more data-efficient model-based learning methods.
Matthew E. Taylor, Nicholas K. Jong, Peter Stone 0001   +2 more
openaire   +2 more sources