Results 51 to 60 of about 404,230 (315)
Enhancing Safe Exploration Through Subgoal Guidance
TechnologiesReinforcement learning is a widely used approach for autonomous navigation, but it often struggles to reach distant, long-horizon goals under safety constraints. The primary reason for this suboptimal performance is that safety requirements significantly
Gregory Gorbov, Aleksandr Panov
doaj +1 more source
Applied Sciences, 2023 This paper proposes a novel solution for using deep neural networks with reinforcement learning as a valid option in negotiating distributed hierarchical controller agents.
Oscar Aponte-Rengifo +2 more
doaj +1 more source
Video Captioning via Hierarchical Reinforcement Learning
, 2018 Video captioning is the task of automatically generating a textual description of the actions in a video. Although previous work (e.g. sequence-to-sequence model) has shown promising results in abstracting a coarse description of a short video, it is ...
Chen, Wenhu +4 more
core +1 more source
Tumor mutational burden as a determinant of metastatic dissemination patterns
Molecular Oncology, EarlyView.This study performed a comprehensive analysis of genomic data to elucidate whether metastasis in certain organs share genetic characteristics regardless of cancer type. No robust mutational patterns were identified across different metastatic locations and cancer types.
Eduardo Candeal +4 more
wiley +1 more source
Hierarchical object detection with deep reinforcement learning [PDF]
, 2016 We present a method for performing hierarchical object detection in images guided by a deep reinforcement learning agent. The key idea is to focus on those parts of the image that contain richer information and zoom on them. We train an intelligent agent
Bellver Bueno, Míriam +3 more
core
Enzymatic degradation of biopolymers in amorphous and molten states: mechanisms and applications
FEBS Open Bio, EarlyView.This review explains how polymer morphology and thermal state shape enzymatic degradation pathways, comparing amorphous and molten biopolymer structures. By integrating structure–reactivity principles with insights from thermodynamics and enzyme engineering, it highlights mechanisms that enable efficient polymer breakdown.
Anđela Pustak, Aleksandra Maršavelski
wiley +1 more source
Automata guided hierarchical reinforcement learning for zero-shot skill composition [PDF]
, 2017 An obstacle that prevents the wide adoption of (deep) reinforcement learning (RL) in control systems is its need for a large amount of interactions with the environment in order to master a skill.
Belta, Calin, Li, Xiao, Ma, Yao
core
Hierarchically Structured Reinforcement Learning for Topically Coherent Visual Story Generation
, 2019 We propose a hierarchically structured reinforcement learning approach to address the challenges of planning for generating coherent multi-sentence stories for the visual storytelling task.
Celikyilmaz, Asli +5 more
core +1 more source
Advanced Functional Materials, EarlyView.Biofabrication aims at providing innovative technologies and tools for the fabrication of tissue‐like constructs for tissue engineering and regenerative medicine applications. By integrating multiple biofabrication technologies, such as 3D (bio) printing with fiber fabrication methods, it would be more realistic to reconstruct native tissue's ...
Waseem Kitana +2 more
wiley +1 more source
Automatic Hierarchical Reinforcement Learning for Reusing Service Process Fragments
IEEE Access, 2021 Prevailing research trend is to use Web services for data publishing and sharing among organizations, but existing works often fall short of service reuse.
Rong Yang, Bing Li, Zhengli Liu
doaj +1 more source