Výsledky vyhledávání - "function approximation errors"

Deep Reinforcement Learning Based Quadrotor Control with Low Function Approximation Errors

Autoři: Zihao Zhang Zhenlin Lu Yongzheng Ren a další

Zdroj: 2024 International Conference on Power Electronics and Artificial Intelligence. :907-911

Piecewise reconstruction of membership function approximation errors for Takagi–Sugeno fuzzy control

Autoři: Wen-Bo Xie Jie Yang Anh-Tu Nguyen a další

Zdroj: Engineering Applications of Artificial Intelligence. 129:107646

Uncertainty-based bootstrapped optimization for offline reinforcement learning.

Autoři: Li, Tianyi Yang, Genke Chu, Jian

Zdroj: International Journal of Machine Learning & Cybernetics; Jun2025, Vol. 16 Issue 5, p3113-3130, 18p

Fixed-time switching tracking control for unmanned helicopter with multiple constraints.

Autoři: Wang, Haibo Shi, Shuang Zhen, Ziyang a další

Zdroj: ISA Transactions. Oct2025, Vol. 165, p268-279. 12p.

Témata: Tracking control systems, Backstepping control method, Observability (Control theory), Drone aircraft, Trajectory measurements, Feedback control systems

Actor Double Critic Architecture for Dialogue System.

Autoři: Saffari, Y. Sartakhti, J. S.

Zdroj: Journal of Electrical & Computer Engineering Innovations (JECEI); Summer/Fall2023, Vol. 11 Issue 2, p363-372, 10p

Témata: ARCHITECTURE, REINFORCEMENT learning, DIALOGUE, ERROR functions, ALGORITHMS, APPROXIMATION error, BOOK industry exhibitions, INDUSTRIAL efficiency, HEURISTIC

LyLA-Therm: Lyapunov-based Langevin Adaptive Thermodynamic Neural Network Controller

Autoři: Akbari, Saiedeh Patil, Omkar Sudhir Dixon, Warren E.

Témata: FOS: Electrical engineering, electronic engineering, information engineering, Systems and Control (eess.SY), Systems and Control

Přístupová URL adresa: http://arxiv.org/abs/2508.14989

Robust Learning-Based Predictive Control for Discrete-Time Nonlinear Systems With Unknown Dynamics and State Constraints.

Autoři: Zhang, Xinglong Liu, Jiahang Xu, Xin a další

Zdroj: IEEE Transactions on Systems, Man & Cybernetics. Systems; Dec2022, Vol. 52 Issue 12, Part 1, p7314-7327, 14p

Témata: NONLINEAR systems, SYSTEM dynamics, DISCRETE-time systems, REINFORCEMENT learning, ONLINE education

Twin Deterministic Policy Gradient Adaptive Dynamic Programming for Optimal Control of Affine Nonlinear Discrete-time Systems.

Autoři: Xu, Jiahui Wang, Jingcheng Rao, Jun a další

Zdroj: International Journal of Control, Automation & Systems; Sep2022, Vol. 20 Issue 9, p3098-3109, 12p

Dual Approximation Policy Optimization

Autoři: Xiong, Zhihan Fazel, Maryam Xiao, Lin

Témata: Computer Science - Machine Learning, text

URL: http://arxiv.org/abs/2410.01249

Exploring Pessimism and Optimism Dynamics in Deep Reinforcement Learning

Autoři: Tasdighi, Bahareh Werge, Nicklas Wu, Yi-Shan a další

Témata: Computer Science - Machine Learning, Statistics - Machine Learning, text

URL: http://arxiv.org/abs/2406.03890

Distributional Soft Actor-Critic: Off-Policy Reinforcement Learning for Addressing Value Estimation Errors.

Autoři: Duan, Jingliang Guan, Yang Li, Shengbo Eben a další

Zdroj: IEEE Transactions on Neural Networks & Learning Systems; Nov2022, Vol. 33 Issue 11, p6584-6598, 15p

Témata: REINFORCEMENT learning, DISTRIBUTION (Probability theory), MAXIMUM entropy method, CONTINUOUS distributions, ARTIFICIAL neural networks, ERROR functions

Massively parallel and universal approximation of nonlinear functions using diffractive processors.

Autoři: Rahman, Md Sadman Sakib Li, Yuhang Yang, Xilin a další

Zdroj: eLight; 11/6/2025, Vol. 5 Issue 1, p1-24, 24p

Diffusion policy with Q-ensemble for offline reinforcement learning.

Autoři: Wang, Dong Zhang, Xu Hua, Qiang a další

Zdroj: International Journal of Machine Learning & Cybernetics; Nov2025, Vol. 16 Issue 11, p9717-9729, 13p

Optimizing task offloading and resource allocation in latency-constrained vehicular edge computing.

Autoři: Li, Bingxian Zhu, Lin Tan, Long

Zdroj: Cluster Computing; 2025, Vol. 28 Issue 8, p1-18, 18p

Minimally Invasive Design and Energy Efficiency Evaluation of Photovoltaic–Energy Storage–Direct Current–Flexible Systems in Low-Carbon Retrofitting of Existing Buildings.

Autoři: Jia, Chenxi Yang, Longyue Jin, Wei a další

Zdroj: Buildings (2075-5309); Oct2025, Vol. 15 Issue 19, p3599, 38p

Témata: PHOTOVOLTAIC power systems, ENERGY storage, RETROFITTING, RETROFITTING of buildings, ENERGY management, REINFORCEMENT learning, ENERGY consumption

Multi-objective energy management strategy for a dual-stack fuel cell heavy-duty truck via deep reinforcement learning.

Autoři: Zhou, Jianhao Zhou, Huanyong Wang, Chunyan a další

Zdroj: Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering (Sage Publications, Ltd.); Oct2025, Vol. 239 Issue 12, p5999-6015, 17p

Deep Reinforcement Learning Research and Applications.

Autoři: Qiu, Yujiang

Zdroj: ITM Web of Conferences; 9/8/2025, Vol. 78, p1-7, 7p

Adaptive Ensemble Q-learning: Minimizing Estimation Bias via Error Feedback

Autoři: Wang, Hang Lin, Sen Zhang, Junshan

Témata: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, text

URL: http://arxiv.org/abs/2306.11918

FAST-Q: Fast-track Exploration with Adversarially Balanced State Representations for Counterfactual Action Estimation in Offline Reinforcement Learning

Autoři: Pulkit Agrawal Rukma Talwadker Aditya Pareek a další

Zdroj: Companion Proceedings of the ACM on Web Conference 2025. :85-94

Témata: FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Machine Learning (cs.LG)

Přístupová URL adresa: http://arxiv.org/abs/2504.21383

Reconstructing models for approximation errors in Takagi–Sugeno fuzzy control under imperfect matching.

Autoři: Yang, Jie Gai, Shao-Yan Da, Fei-Peng

Zdroj: Applied Soft Computing. Sep2025, Vol. 181, pN.PAG-N.PAG. 1p.

Témata: Fuzzy control systems, Approximation error, Stability criterion, Membership functions (Fuzzy logic), Uncertainty (Information theory), Robust control, Stability theory