Results 21 to 30 of about 404,230 (315)
IEEE Access, 2022 Military vehicle object detection technology in complex environments is the basis for the implementation of reconnaissance and tracking tasks for weapons and equipment, and is of great significance for information and intelligent combat.
Yan Ouyang +4 more
doaj +1 more source
HLifeRL: A hierarchical lifelong reinforcement learning framework
Journal of King Saud University: Computer and Information Sciences, 2022 Deep reinforcement learning research in a single-task environment has made remarkable achievements. However, it is often plagued by catastrophic forgetting, prohibitively low sample efficiency and lack of scalability problems when facing multi-task ...
Fan Ding, Fei Zhu
doaj +1 more source
3D reconstruction based on hierarchical reinforcement learning with transferability
Integr. Comput. Aided Eng., 2023 3D reconstruction is extremely important in CAD (computer-aided design)/CAE (computer-aided Engineering)/CAM (computer-aided manufacturing). For interpretability, reinforcement learning (RL) is used to reconstruct 3D shapes from images by a series of ...
Lan Li +4 more
semanticscholar +1 more source
IEEE Access, 2018 In recent years, reinforcement learning (RL) has achieved remarkable success due to the growing adoption of deep learning techniques and the rapid growth of computing power.
Tuyen P. Le +2 more
doaj +1 more source
A Hierarchical Framework for Quadruped Robots Gait Planning Based on DDPG
Biomimetics, 2023 In recent years, significant progress has been made in employing reinforcement learning for controlling legged robots. However, a major challenge arises with quadruped robots due to their continuous states and vast action space, making optimal control ...
Yanbiao Li +4 more
doaj +1 more source
Hierarchical Reinforcement Learning With Guidance for Multi-Domain Dialogue Policy
IEEE/ACM Transactions on Audio Speech and Language Processing, 2023 Achieving high performance in a multi-domain dialogue system with low computation is undoubtedly challenging. Previous works applying an end-to-end approach have been very successful.
Mahdin Rohmatillah, Jen-Tzung Chien
semanticscholar +1 more source
Hierarchical Reinforcement Learning [PDF]
, 1993 A response generating system can be seen as a mapping from a set of external states (inputs) to a set of actions (outputs). This mapping can be done in principally different ways. One method is to divide the state space into a set of discrete states and store the optimal response for each state. This is denominated a memory mapping system.
openaire +3 more sources
LLM-Based Intent Processing and Network Optimization Using Attention-Based Hierarchical Reinforcement Learning [PDF]
IEEE Wireless Communications and Networking ConferenceIntent-based network automation is a promising tool that enables easier network management; however, certain challenges must be addressed effectively. These are: 1) processing intents, i.e., identification of logic and necessary parameters to fulfill an ...
Md Arafat Habib +6 more
semanticscholar +1 more source
Intelligent Attack Path Discovery Based on Hierarchical Reinforcement Learning [PDF]
Jisuanji kexue, 2023 Intelligent attack path discovery is a key technology for automated penetration testing,but existing methods face the problems of exponential growth of state and action space and sparse rewards,which make the algorithm difficult to converge.To this end ...
ZENG Qingwei, ZHANG Guomin, XING Changyou, SONG Lihua
doaj +1 more source
Adjacency Constraint for Efficient Hierarchical Reinforcement Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 Goal-conditioned Hierarchical Reinforcement Learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the goal space, is large.
Tianren Zhang +4 more
openaire +3 more sources