Results 41 to 50 of about 6,304,901 (198)

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

ZX-Diagram T-Count Reduction Based on Proximal Policy Optimization

Intelligent Computing
In fault-tolerant quantum computing systems, the T gates consume more fault-tolerant resources. In this paper, we propose an automated optimization method based on the Proximal Policy Optimization (PPO) algorithm. We first translate quantum circuits into
Keyu Xiong, Tao Shang, Chenyi Zhang, Yuchen Liu   +3 more
doaj   +1 more source

EFFECTIVENESS OF PROXIMAL POLICY OPTIMIZATION METHODS FOR NEURAL PROGRAM INDUCTION [PDF]

, 2020
The Neural Virtual Machine (NVM) is a novel neurocomputational architecturedesigned to emulate the functionality of a traditional computer. A version of the NVM called NVM-RL supports reinforcement learning based on standard policy gradient methods as a ...
Lin, Runxing
core   +1 more source

Reinforcement Learning With a Low‐Cost Parallel Linkage Gripper for Static and Dynamic Planar In‐Hand Manipulation

Advanced Intelligent Systems, EarlyView.
Hardware‐learning co‐design combines volar‐plate‐inspired passive‐joint constraints with mechanism‐aware reinforcement learning for a low‐cost parallel‐linkage gripper. The resulting system performs quasi‐static object adjustment and dynamic pinch grasping, demonstrating reliable planar in‐hand manipulation and successful sim‐to‐real transfer. Parallel
Yanzhou Jin, Adam J. Spiers, Yusuke Iwasawa, Yutaka Matsuo, Yaonan Zhu   +4 more
wiley   +1 more source

Dual‐View Representation Learning for Deployable Humanoid Whole‐Body Control

Advanced Intelligent Systems, EarlyView.
Humanoid robots must learn control from limited onboard sensing, although simulation provides richer training‐only states. DVP learning pairs these views of each simulated motion and aligns their latent control features inside the policy‐learning loop. This direct, deployment‐aware supervision accelerates learning while the deployed policy relies only ...
Haolin Song, Wengang Zhou, Mingxiao Feng, Houqiang Li   +3 more
wiley   +1 more source

Multi-Layer Energy Management and Strategy Learning for Microgrids: A Proximal Policy Optimization Approach

Energies
An efficient energy management system (EMS) enhances microgrid performance in terms of stability, safety, and economy. Traditional centralized or decentralized energy management systems are unable to meet the increasing demands for autonomous decision ...
Xiaohan Fang, Peng Hong, Shuping He, Yuhao Zhang, Di Tan   +4 more
doaj   +1 more source

Gradient Informed Proximal Policy Optimization

, 2023
We introduce a novel policy learning method that integrates analytical gradients from differentiable environments with the Proximal Policy Optimization (PPO) algorithm.
Son, Sanghyun, Sullivan, Ryan, Zheng, Laura Yu, Qiao, Yi-Ling, Lin, Ming C.   +4 more
core  

Artificial Intelligence‐Driven Natural Product Drug Discovery: From Computational Genome Mining to Clinical Translation

Medicinal Research Reviews, EarlyView.
ABSTRACT Natural products (NPs) have historically yielded numerous therapeutic agents, yet their integration into modern drug discovery has been constrained by chemical complexity, low abundance, laborious dereplication, and limited target annotation.
Antonio Lavecchia
wiley   +1 more source

Safeguarded Reinforcement Learning for Dynamic Environments

Optimal Control Applications and Methods, EarlyView.
This paper uses a combination of Reinforcement Learning and Funnel Control to train a fast and safe controller for systems operating in changing environments. Furthermore, the presented formulation overcomes former limitations associated with the need for predefined reference trajectories.
Simon Gottschalk
wiley   +1 more source

Modeling of adaptive UAV route control based on reinforcement learning algorithms

Сучасний стан наукових досліджень та технологій в промисловості
Subject matter is the reward function, action policy, and learning dynamics of the Proximal Policy Optimization (PPO) algorithm in the task of adaptive UAV navigation under dynamic airspace conditions and limited energy resources.
Максим Єна, Ольга Погудіна   +1 more
doaj   +3 more sources