Search Results - "Q-learning with linear function approximation"

Regularized Q-Learning With Linear Function Approximation

Authors: Xi, Jiachen Garcia, Alfredo Momcilovic, Petar

Source: IEEE Transactions on Automatic Control. :1-8

Subject Terms: FOS: Computer and information sciences, 0209 industrial biotechnology, Artificial Intelligence (cs.AI), 0203 mechanical engineering, Computer Science - Artificial Intelligence, 02 engineering and technology

Access URL: http://arxiv.org/abs/2401.15196

Distributed Multi-Agent Gradient Based Q-Learning with Linear Function Approximation

Authors: Miloš S. Stanković Marko Beko Srdjan S. Stanković

Source: 2024 European Control Conference (ECC). :2500-2505

Regularized Q-Learning with Linear Function Approximation

Authors: Xi, Jiachen Garcia, Alfredo Momcilovic, Petar

Index Terms: Computer Science - Artificial Intelligence, text

URL: http://arxiv.org/abs/2401.15196

Finite-sample Guarantees for Nash Q-learning with Linear Function Approximation

Authors: Cisneros-Velarde, Pedro Koyejo, Sanmi

Index Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, text

URL: http://arxiv.org/abs/2303.00177

Multi-Bellman operator for convergence of $Q$-learning with linear function approximation

Authors: Carvalho, Diogo S. Santos, Pedro A. Melo, Francisco S.

Index Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, text

URL: http://arxiv.org/abs/2309.16819

Multiscale Q-learning with linear function approximation

Authors: Bhatnagar, Shalabh Lakshmanan, K

Source: Discrete Event Dynamic Systems. 26:477-509

Subject Terms: 0209 industrial biotechnology, 0203 mechanical engineering, Computer Science & Automation (Formerly, School of Automation), 02 engineering and technology

File Description: application/pdf

Access URL: http://eprints.iisc.ac.in/id/eprint/54360
https://www.amrita.edu/publication/multiscale-q-learning-linear-function-approximation
https://dblp.uni-trier.de/db/journals/deds/deds26.html#BhatnagarL16
https://link.springer.com/content/pdf/10.1007%2Fs10626-015-0216-z.pdf
https://dl.acm.org/doi/10.1007/s10626-015-0216-z
https://link.springer.com/article/10.1007/s10626-015-0216-z

LinFa-Q: Accurate Q-learning with linear function approximation

Authors: Zhechao Wang Qiming Fu Jianping Chen et al.

Source: Neurocomputing. 611:128654

Convergence of Q-learning with linear function approximation

Authors: M. Isabel Ribeiro Francisco S. Melo

Source: 2007 European Control Conference (ECC). :2671-2678

Subject Terms: 0209 industrial biotechnology, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology

Access URL: https://ieeexplore.ieee.org/document/7068926/

Q-Learning with Linear Function Approximation

Authors: Francisco S. Melo M. Isabel Ribeiro

Source: Lecture Notes in Computer Science ISBN: 9783540729259

Subject Terms: 4. Education

Access URL: https://rd.springer.com/chapter/10.1007/978-3-540-72927-3_23
http://www.ausy.tu-darmstadt.de/uploads/Research/MPI2007/TechReport.pdf
http://lrm.isr.ist.utl.pt/lrm/ps/07-COLT-QLPO.pdf
http://www.ausy.tu-darmstadt.de/uploads/Research/MPI2007/MPI2007melo2.pdf
https://dblp.uni-trier.de/db/conf/colt/colt2007.html#MeloR07
https://link.springer.com/chapter/10.1007%2F978-3-540-72927-3_23

Linfa-Q: Accurate Q-Learning with Linear Function Approximation

Authors: Wang, Zhechao Fu, Qiming Chen, Jianping et al.

Availability: http://dx.doi.org/10.2139/ssrn.4506770

Multiscale Q-learning with linear function approximation.

Authors: Bhatnagar, Shalabh Lakshmanan, K.

Source: Discrete Event Dynamic Systems; Sep2016, Vol. 26 Issue 3, p477-509, 33p

Applying Reinforcement Learning Techniques for Emergency Resource Dispatch

Authors: Garriga Orteu, Anna Martín Muñoz, Mario Robert, Stephan et al.

Contributors: Garriga Orteu, Anna Martín Muñoz, Mario Robert, Stephan et al.

Source: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

Subject Terms: Artificial intelligence, Safe Reinforcement Learning, Interreg Europeu, Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial, Ambulance Dispatch, Deep Q-Learning, European Interreg, SIA-REMU Project, Enviament d'Ambulàncies, Double Deep Q-Learning, Q-Learning with Linear Function Approximation, Machine Learning, Aprenentatge per Reforç Amb Aproximació dels Valors Estat-Acció, Gestió de Recursos Médics, Aprenentatge per Reforç amb Aversió al Risc, Artificial Intelligence, Aprenentatge per Reforç Segur, Machine learning, Reinforcement learning, Aprenentatge automàtic, Intel·ligència Artificial, Risk-Averse Reinforcement Learning, Projecte SIA-REMU, Ambulance service, Aprenentatge Automàtic, Soft Actor-Critic, Intel·ligència artificial, Aprenentatge per Reforç, Reinforcement Learning, Actor-Critic Methods, Safe Model-Based Policy Optimization, Mètodes d'Actor-Crític, Reinforcement Learning Approximating the State-Action Values, Aprenentatge per reforç, Servei d'ambulàncies, Q-Learning amb Aproximació Lineal de Funcions, Management of Medical Resources

File Description: application/pdf

Access URL: https://hdl.handle.net/2117/405691

Q-Learning with Linear Function Approximation.

Authors: Carbonell, Jaime G. Siekmann, Jörg Bshouty, Nader H. et al.

Source: Learning Theory (9783540729259). 2007, p308-322. 15p.

Convergence of Q-learning with linear function approximation

Authors: Francisco S. Melo The Pennsylvania State University CiteSeerX Archives

Contributors: Francisco S. Melo The Pennsylvania State University CiteSeerX Archives

Source: http://welcome.isr.ist.utl.pt/img/pdfs/1636_ECC07QLFA-Proceedings.pdf.

File Description: application/pdf

Relation: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.99.4591

Availability: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.99.4591
http://welcome.isr.ist.utl.pt/img/pdfs/1636_ECC07QLFA-Proceedings.pdf

Convergence of Q-learning with linear function approximation.

Authors: Melo, Francisco S. Ribeiro, M. Isabel

Source: 2007 European Control Conference (ECC); 2007, p2671-2678, 8p

Linear $Q$-Learning Does Not Diverge in $L^2$: Convergence Rates to a Bounded Set

Authors: Liu, Xinyu Xie, Zixuan Zhang, Shangtong

Index Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning, text

URL: http://arxiv.org/abs/2501.19254

Applying Reinforcement Learning Techniques for Emergency Resource Dispatch

Authors: Universitat Politècnica de Catalunya. Departament de Ciències de la Computació Martín Muñoz, Mario Robert, Stephan et al.

Index Terms: Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial, Artificial intelligence, Machine learning, Reinforcement learning, Ambulance service, Intel·ligència Artificial, Aprenentatge Automàtic, Aprenentatge per Reforç, Aprenentatge per Reforç Segur, Enviament d'Ambulàncies, Gestió de Recursos Médics, Interreg Europeu, Projecte SIA-REMU, Aprenentatge per Reforç Amb Aproximació dels Valors Estat-Acció, Mètodes d'Actor-Crític, Aprenentatge per Reforç amb Aversió al Risc, Q-Learning amb Aproximació Lineal de Funcions, Deep Q-Learning, Double Deep Q-Learning, Soft Actor-Critic, Safe Model-Based Policy Optimization, Artificial Intelligence, Machine Learning, Reinforcement Learning, Safe Reinforcement Learning, Ambulance Dispatch, Management of Medical Resources, European Interreg, SIA-REMU Project, Reinforcement Learning Approximating the State-Action Values, Actor-Critic Methods, Risk-Averse Reinforcement Learning, Q-Learning with Linear Function Approximation, Intel·ligència artificial, Aprenentatge automàtic, Aprenentatge per reforç, Servei d'ambulàncies, Master thesis

URL: http://hdl.handle.net/2117/405691

Gradient-Based Algorithms for Zeroth-Order Optimization.

Authors: L. A., Prashanth Bhatnagar, Shalabh

Source: Foundations & Trends in Optimization; 2025, Vol. 8 Issue 1-3, p1-332, 332p

Stochastic First-Order Methods for Average-Reward Markov Decision Processes.

Authors: Li, Tianjiao Wu, Feiyang Lan, Guanghui

Source: Mathematics of Operations Research; Nov2025, Vol. 50 Issue 4, p3125-3160, 36p

Subject Terms: MARKOV processes, REINFORCEMENT learning, STOCHASTIC analysis, UNIVERSITY research

Reformulating Q-Learning as a Hybrid Classifier for Predictive Marketing Analytics.

Authors: Lubis, Andre Hasudungan Sihombing, Poltak Nababan, Erna Budhiarti et al.

Source: International Journal of Intelligent Engineering & Systems; 2025, Vol. 18 Issue 11, p29-44, 16p

Subject Terms: SUPERVISED learning, REINFORCEMENT learning, MACHINE learning, MARKETING forecasting, CUSTOMER retention, CLASSIFICATION