Results 121 to 130 of about 6,522,305 (296)

RL-I2IT: Image-to-image translation with deep reinforcement learning

Neural Networks
Most existing Image-to-Image Translation (I2IT) methods generate images in a single run of a deep learning (DL) model. However, designing such a single-step model is always challenging, requiring a huge number of parameters and easily falling into bad global minimums and overfitting.
Jing Hu, Ziwei Luo, Chengming Feng, Shu Hu, Bin Zhu, Xi Wu, Xin Li, Hongtu Zhu, Siwei Lyu, Xin Wang   +9 more
openaire   +4 more sources

Teaching an AI agent how to drive on complex racetracks using reinforcement learning

, 2023
The main objective of this thesis is to educate a reinforcement learning (RL) agent on acquiring the skill of driving a car in the Unity environment. The central focus of this thesis is to train a reinforcement learning (RL) agent utilizing a deep neural
Qin, Yuchen
core  

Behaviorally Adaptive and Inclusive Advanced Driver‐Assistance Systems

Advanced Intelligent Systems, EarlyView.
Advanced driver‐assistance systems (ADASs) are mapped as evolving human‐centered, adaptive technologies linking sensing, driver monitoring, AR/HUD interfaces, patents, regulation, and inclusive design. The review identifies gaps in real‐world evidence, diverse‐driver validation, gaze metrics, and governance, outlining a roadmap for safer, behaviorally ...
Jana Skirnewskaja, Mardavij Roozbehani, Munther A. Dahleh   +2 more
wiley   +1 more source

Application of Reinforcement Learning in Controlling Quadrotor UAV Flight Actions

Drones
Most literature has extensively discussed reinforcement learning (RL) for controlling rotorcraft drones during flight for traversal tasks. However, most studies lack adequate details regarding the design of reward and punishment mechanisms, and there is ...
Shang-En Shen, Yi-Cheng Huang
doaj   +1 more source

Benchmarking Data‐Driven Control of Octopus‐Inspired Soft Arms in Underwater Environment

Advanced Intelligent Systems, EarlyView.
Underwater soft robots present safe, compliant interaction, yet reproducible control remains scarce. This work presents an open benchmark for octopus‐inspired arms: a smooth, velocity‐diverse data‐collection scheme produces a compact dataset to train a vanilla policy.
Muhammad Sunny Nazeer, Yasmin Tauqeer Ansari, Emanuele Solfiti, Baljinder Singh Bal, Matteo Lo Preti, Barbara Mazzolai, Cecilia Laschi   +6 more
wiley   +1 more source

A framework for the robot skill learning using reinforcement learning

, 2003
Robot acquiring skill is a process similar to human skill learning. Reinforcement learning (RL) is an on-line actor critic method for a robot to develop its skill.
Zhao MY(赵明扬), Wei YZ(魏英姿)
core   +1 more source

Exploiting Edge Semantics in Job Shop Scheduling Problem With Heterogeneous Graph Transformers

Advanced Intelligent Systems, EarlyView.
A heterogeneous graph transformer (HGT) is introduced for reinforcement learning‐based job shop scheduling by explicitly distinguishing precedence and machine‐contention relations through edge‐type‐specific attention. The proposed framework learns richer scheduling representations, improves decision quality over homogeneous graph models, and highlights
Bulent Soykan, Fatih Kasimoglu
wiley   +1 more source

MLP-RL-CRD: diagnosis of cardiovascular risk in athletes using a reinforcement learning-based multilayer perceptron

, 2023
Objective. Pre-participation medical screening of athletes is necessary to pinpoint individuals susceptible to cardiovascular events. Approach. The article presents a reinforcement learning (RL)-based multilayer perceptron, termed MLP-RL-CRD, designed to
Ru-San Tan (435098), Roohallah Alizadehsani (13057710), Muhammad Mehrtash (17722245), Marzieh Mirzaeibonehkhater (17722239), Arsam Bostani (17722236), Hamidreza Najafi (17722242), Rajendra Acharya (1390232)   +6 more
core   +1 more source

Reinforced-lib: Rapid prototyping of reinforcement learning solutions

SoftwareX
Reinforcement learning (RL) is emerging as a promising framework for training intelligent agents to solve complex problems. However, developing RL solutions involves a complex process that requires experimenting with different models, agents, and ...
Maksymilian Wojnar, Szymon Szott, Krzysztof Rusek, Wojciech Ciezobka   +3 more
doaj   +1 more source

Bayesian Optimization–Reinforcement Learning Hybrid Framework for a‐IGZO Thin‐Film Transistor Compact Model Parameter Extraction in 2T0C Dynamic Random Access Memory Applications

Advanced Intelligent Systems, EarlyView.
A training‐free two‐stage BO–RL framework extracts compact model parameters for a‐IGZO TFTs, reaching BO‐level fitting quality at a constant per‐simulation optimization cost. Bayesian optimization performs exploration and provides an optimized starting point.
Seunghyun Son, Taejun Ha, Taeyoung Nam, Yoonyoung Chung, Sunmean Kim   +4 more
wiley   +1 more source