bibliography.bib

@article{Nadaraya1964,
	author = {Nadaraya, E. A.},
	title = {On Estimating Regression},
	journal = {Theory of Probability \& Its Applications},
	volume = {9},
	number = {1},
	pages = {141-142},
	year = {1964},
	doi = {10.1137/1109020},
}

@Article{Leite2025,
	AUTHOR = {Leite, Denis and Andrade, Emmanuel and Rativa, Diego and Maciel, Alexandre M. A.},
	TITLE = {Fault Detection and Diagnosis in Industry 4.0: A Review on Challenges and Opportunities},
	JOURNAL = {Sensors},
	VOLUME = {25},
	YEAR = {2025},
	NUMBER = {1},
	ARTICLE-NUMBER = {60},
	URL = {https://www.mdpi.com/1424-8220/25/1/60},
	ISSN = {1424-8220},
	DOI = {10.3390/s25010060}
}

@misc{Hexagon2024,
	note = {[Online; accessed 2025-01-03]},
	author = {{Hexagon}},
	year = {2024},
	month = {mar 7},
	title = {98% manufacturers face data woes that stifle innovation and time to market, {Hexagon}\textquoteright{}s report reveals},
	howpublished = {https://hexagon.com/company/newsroom/press-releases/2024/98-percent-manufacturers-face-data-woes-that-stifle-innovation-and-time-to-market},
}

@article{Lavet2016,
	author       = {Vincent Fran{\c{c}}ois{-}Lavet and
	Rapha{\"{e}}l Fonteneau and
	Damien Ernst},
	title        = {How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies},
	journal      = {CoRR},
	volume       = {abs/1512.02011},
	year         = {2016},
	url          = {http://arxiv.org/abs/1512.02011},
	eprinttype    = {arXiv},
	biburl       = {https://dblp.org/rec/journals/corr/Francois-LavetF15.bib},
}


%% === ML baselines 
@article{liu2020-92ML,
	title={Calibration-based tool condition monitoring for repetitive machining operations},
	author={Liu, Rui and Kothuru, Achyuth and Zhang, Shuhuan},
	journal={Journal of Manufacturing Systems},
	volume={54},
	pages={285--293},
	year={2020},
	publisher={Elsevier}
}
@article{niu2020-93ML,
	title={Multisensory based tool wear monitoring for practical applications in milling of titanium alloy},
	author={Niu, Boya and Sun, Jie and Yang, Bin},
	journal={Materials today: proceedings},
	volume={22},
	pages={1209--1217},
	year={2020},
	publisher={Elsevier}
}

@article{yang2020-94ML,
	title={Vibration singularity analysis for milling tool condition monitoring},
	author={Yang, Bin and Guo, Kai and Liu, Jiangwei and Sun, Jie and Song, Ge and Zhu, Shaowei and Sun, Chao and Jiang, Zhenxi and others},
	journal={International Journal of Mechanical Sciences},
	volume={166},
	pages={105254},
	year={2020},
	publisher={Elsevier}
}

@article{lei2020-95ML,
	title={Applications of machine learning to machine fault diagnosis: A review and roadmap},
	author={Lei, Yaguo and Yang, Bin and Jiang, Xinwei and Jia, Feng and Li, Naipeng and Nandi, Asoke K},
	journal={Mechanical systems and signal processing},
	volume={138},
	pages={106587},
	year={2020},
	publisher={Elsevier}
}
@article{zhou2020-96ML,
	title={Tool condition monitoring in milling using a force singularity analysis approach},
	author={Zhou, Chang’an and Guo, Kai and Sun, Jie and Yang, Bin and Liu, Jiangwei and Song, Ge and Sun, Chao and Jiang, Zhenxi},
	journal={The International Journal of Advanced Manufacturing Technology},
	volume={107},
	pages={1785--1792},
	year={2020},
	publisher={Springer}
}

@inproceedings{patange2019-23ML,
	title={Milling cutter condition monitoring using machine learning approach},
	author={Patange, AD and Jegadeeshwaran, R and Dhobale, NC},
	booktitle={IOP Conference Series: Materials Science and Engineering},
	volume={624},
	number={1},
	pages={012030},
	year={2019},
	organization={IOP Publishing}
}

@article{madhusudana2016-64ML,
	title={Condition monitoring of face milling tool using K-star algorithm and histogram features of vibration signal},
	author={Madhusudana, CK and Kumar, Hemantha and Narendranath, S},
	journal={Engineering science and technology, an international journal},
	volume={19},
	number={3},
	pages={1543--1551},
	year={2016},
	publisher={Elsevier}
}


@article{ou2020-97ML,
	title={A novel order analysis and stacked sparse auto-encoder feature learning method for milling tool wear condition monitoring},
	author={Ou, Jiayu and Li, Hongkun and Huang, Gangjin and Zhou, Qiang},
	journal={Sensors},
	volume={20},
	number={10},
	pages={2878},
	year={2020},
	publisher={MDPI}
}







@inproceedings{IEEE-PHM-2012,
	title={PRONOSTIA: an experimental platform for bearings accelarated life test},
	author={Nectoux, P and Gouriveau, R and Medjaher, K and Ramasso, E and Morello, B and Zerhouni, N and Varnier, C},
	booktitle={Proceedings of the IEEE International Conference on Prognostics and Health Management, Denver, CO, USA},
	volume={20},
	year={2012}
}

@article{CWRU-2019,
	title={CWRU bearing dataset and Gearbox dataset of IEEE PHM Challenge Competition in 2009},
	author={Li, Zhenxiang},
	journal={IEEE Dataport},
	year={2019}
}

@article{Patange2021Review,
	note = {[Online; accessed 2024-12-26]},
	author = {Patange, Abhishek D. and Jegadeeshwaran, R.},
	journal = {Materials Today: Proceedings},
	year = {2021},
	pages = {1106--1115},
	publisher = {Elsevier BV},
	title = {Review on tool condition classification in milling: A machine learning approach},
	volume = {46},
}
@article{Siraskar2024ML,
	note = {[Online; accessed 2024-12-26]},
	author = {Siraskar, Rajesh and Kumar, Satish and Patil, Shruti and Bongale, Arunkumar and Kotecha, Ketan},
	journal = {MethodsX},
	year = {2024},
	month = {6},
	pages = {102754},
	publisher = {Elsevier BV},
	title = {Application of the {Nadaraya}-{Watson} Estimator based Attention Mechanism to the Field of Predictive aintenance},
	volume = {12},
}
@article{fu2023ML,
	title={EdgeCog: a real-time bearing fault diagnosis system based on lightweight edge computing},
	author={Fu, Lei and Yan, Ke and Zhang, Yikun and Chen, Ruien and Ma, Zepeng and Xu, Fang and Zhu, Tiantian},
	journal={IEEE Transactions on Instrumentation and Measurement},
	year={2023},
	publisher={IEEE}
}

@article{pandey2023ML,
	title={Towards deploying DNN models on edge for predictive maintenance applications},
	author={Pandey, Rick and Uziel, Sebastian and Hutschenreuther, Tino and Krug, Silvia},
	journal={Electronics},
	volume={12},
	number={3},
	pages={639},
	year={2023},
	publisher={MDPI}
}

@article{lu2021ML,
	title={Kernel-based dynamic ensemble technique for remaining useful life prediction},
	author={Lu, Hsuan-Wen and Lee, Chia-Yen},
	journal={IEEE Robotics and Automation Letters},
	volume={7},
	number={2},
	pages={1142--1149},
	year={2021},
	publisher={IEEE}
}

%% REINFORCE lecture
@misc{Matni2019,
	author = {Matni, Nikolai},
	title = {ESE 680-004: Learning and {Control} - {Lecture} 20: Model {Free} {Methods}},
	year = {2019},
	publisher = {University of Pennsylvania},
	howpublished = {https://nikolaimatni.github.io/courses/ese680-fall2019/scribe-notes/lecture21.pdf},
}



%% === Empirical research
@misc{Politzer2021,
	note = {[Online; accessed 2024-12-28]},
	author = {Politzer-Ahles, Stephen},
	year = {2021},
	month = {may 2},
	title = {Exploratory vs. confirmatory research},
	howpublished = {https://www.polyu.edu.hk/cbs/sjpolit/classes/cbs6442/TypesOfResearchDesigns/exploratory-vs-confirmatory.html},
}

@article{Gamper2017,
	note = {[Online; accessed 2024-12-29]},
	year = {2017},
	author = {Gamper, J.},
	journal = {Faculty of Engineering Free University of Bozen-Bolzano},
	title = {RESEARCH {METHODS} empirical/experimental {CS} research methods},
	howpublished = {https://www.inf.unibz.it/\textasciitilde{}calvanese/teaching/2017-02-PhD-RM/RM-2017-M4-gamper.pdf},
}

@misc{Bouchrika2024,
	note = {[Online; accessed 2024-12-26]},
	author = {Bouchrika, Imed},
	year = {2024},
	month = {Nov 19},
	title = {What is empirical research? {Definition}, types and samples in 2024},
	howpublished = {https://research.com/research/what-is-empirical-research},
}

@Inbook{Germann2023,
	author={Germann, Cornel},
	title={Methodology and Empirical Research},
	bookTitle={Chairperson Succession: Competences, Moderators, and Disclosure},
	year={2023},
	publisher={Springer Fachmedien Wiesbaden},
	address={Wiesbaden},
	pages={87--98},
	isbn={978-3-658-40817-6},
	doi={10.1007/978-3-658-40817-6_5},
	url={https://doi.org/10.1007/978-3-658-40817-6_5}
}

@misc{Emerald2021,
	note = {[Online; accessed 2024-12-26]},
	year = {2021},
	title = {Conduct empirical research},
	publisher = {Emerald Publishing Limited},
	howpublished = {https://www.emeraldgrouppublishing.com/how-to/research-methods/conduct-empirical-research#theoretical-framework},
}

@inbook{DeGroot1969,
	url = {https://doi.org/10.1515/9783112313121-003},
	title = {The Empirical Cycle In Science},
	booktitle = {Methodology: Foundations of inference and research in the behavioral sciences},
	author = {Adriaan D. De Groot and Spiekerman J. A. A.},
	publisher = {De Gruyter Mouton},
	address = {Berlin, Boston},
	pages = {1--32},
	doi = {doi:10.1515/9783112313121-003},
	isbn = {9783112313121},
	year = {1969},
	lastchecked = {2024-12-28}
}


% ------------------------- 23-Dec-2024 -------------------------

%% === REINFORCE specific
@misc{Jayakody2023REINFORCE,
	note = {[Online; accessed 2024-12-23]},
	author = {Jayakody, Dilith},
	year = {2023},
	month = {feb 13},
	title = {REINFORCE - {A} quick introduction (with code)},
	howpublished = {https://dilithjay.com/blog/reinforce-a-quick-introduction-with-code},
}

%% ===== SUPPORT FOR SIMPLE ALGOS ! ===== 

@article{mania2018,
      title={Simple random search provides a competitive approach to reinforcement learning}, 
      author={Horia Mania and Aurelia Guy and Benjamin Recht},
      year={2018},
      eprint={1803.07055},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/1803.07055}, 
}

% ------------------------- 22-Dec-2024 -------------------------

%% ===== AutoRL ! ===== 
@inproceedings{Eimer2023AutoRL,
  title={Hyperparameters in reinforcement learning and how to tune them},
  author={Eimer, Theresa and Lindauer, Marius and Raileanu, Roberta},
  booktitle={International Conference on Machine Learning},
  pages={9104--9149},
  year={2023},
  organization={PMLR}
}

%% ===== Training time ===== 
@article{Yang2023ReducingTime,
	note = {[Online; accessed 2024-12-22]},
	author = {Yang, Junjun and Tan, Kaige and Feng, Lei and El-Sherbeeny, Ahmed M. and Li, Zhiwu},
	journal = {IEEE Access},
	year = {2023},
	pages = {59840--59853},
	publisher = {{Institute of Electrical and Electronics Engineers (IEEE)}},
	title = {Reducing the learning time of reinforcement learning for the supervisory control of discrete event systems},
	volume = {11},
}

@misc{Ganeshkumar2020Minimising,
	note = {[Online; accessed 2024-12-22]},
	author = {Ganeshkumar, M},
	year = {2020},
	month = {jan 20},
	publisher = {National University of Singapore},
	title = {Minimising {Processing} {Time} when {Training} {Deep} {Reinforcement} {Learning} {Models}},
}

@misc{Anderlini2019,
	note = {[Online; accessed 2024-12-22]},
	author = {Anderlini, Enrico},
	year = {2019},
	month = {dec 13},
	title = {Measures to improve computation time with reinforcement learning block in {Simulink}},
	howpublished = {https://www.mathworks.com/matlabcentral/answers/496460-measures-to-improve-computation-time-with-reinforcement-learning-block-in-simulink#answer\textunderscore{}412231},
}

%% ===== AutoML ===== 
@inbook{Tornede2020AutoML,
	note = {[Online; accessed 2024-12-21]},
	address = {Cham},
	author = {Tornede, Tanja and Tornede, Alexander and Wever, Marcel and Mohr, Felix and H{\" u}llermeier, Eyke},
	booktitle = {Communications in {Computer} and {Information} {Science}},
	year = {2020},
	pages = {106--118},
	publisher = {Springer International Publishing},
	title = {AutoML for Predictive Maintenance: One tool to {RUL} them all},
}


@article{krzywanski2024AutoML,
  title={AutoML-based predictive framework for predictive analysis in adsorption cooling and desalination systems},
  author={Krzywanski, Jaroslaw and Sztekler, Karol and Skrobek, Dorian and Grabowska, Karolina and Ashraf, Waqar Muhammad and Sosnowski, Marcin and Ishfaq, Kashif and Nowak, Wojciech and Mika, Lukasz},
  journal={Energy Science \& Engineering},
  volume={12},
  number={5},
  pages={1969--1986},
  year={2024},
  publisher={Wiley Online Library}
}

@article{OLeary2023AutoML,
  title={A Review of AutoML Software Tools for Time Series Forecasting and Anomaly Detection.},
  author={O'Leary, Christian and Toosi, Farshad Ghassemi and Lynch, Conor},
  journal={ICAART (3)},
  pages={421--433},
  year={2023}
}

@article{Thessen2016,
	author = {Anne E Thessen},
	title = {Adoption of Machine Learning Techniques in Ecology and Earth Science},
	volume = {1},
	number = {},
	year = {2016},
	doi = {10.3897/oneeco.1.e8621},
	publisher = {Pensoft Publishers},
	abstract = {},
	issn = {},
	pages = {e8621},
	URL = {https://doi.org/10.3897/oneeco.1.e8621},
	eprint = {https://doi.org/10.3897/oneeco.1.e8621},
	journal = {One Ecosystem}
}



% ------------------------- 29-Sept-2023 -------------------------
@article{autorl:parker2022,
	title={Automated Reinforcement Learning (AutoRL): A Survey and Open Problems},
	author={Parker-Holder, Jack and Rajan, Raghu and Song, Xingyou and Biedenkapp, Andr{\'e} and Miao, Yingjie and Eimer, Theresa and Zhang, Baohe and Nguyen, Vu and Calandra, Roberto and Faust, Aleksandra and others},
	journal={Journal of Artificial Intelligence Research},
	volume={74},
	pages={517--568},
	year={2022},
}

@article{sayyad2023,
	title={Remaining Useful-Life Prediction of the Milling Cutting Tool Using Time--Frequency-Based Features and Deep Learning Models},
	author={Sayyad, Sameer and Kumar, Satish and Bongale, Arunkumar and Kotecha, Ketan and Abraham, Ajith},
	journal={Sensors},
	volume={23},
	number={12},
	pages={5659},
	year={2023},
	publisher={MDPI}
}

@inproceedings{andrychowicz2021matters,
	title={What Matters for On-Policy Deep Actor-Critic Methods? a Large-Scale Study},
	author={Andrychowicz, Marcin and Raichuk, Anton and Sta{\'n}czyk, Piotr and Orsini, Manu and Girgin, Sertan and Marinier, Rapha{\"e}l and Hussenot, Leonard and Geist, Matthieu and Pietquin, Olivier and Michalski, Marcin and others},
	booktitle={International conference on learning representations},
	year={2021}
}

@inproceedings{autorl:shala2022,
	title={Auto{RL}-Bench 1.0},
	author={Gresa Shala and Sebastian Pineda Arango and Andr{\'e} Biedenkapp and Frank Hutter and Josif Grabocka},
	booktitle={Sixth Workshop on Meta-Learning at the Conference on Neural Information Processing Systems},
	year={2022},
	url={https://openreview.net/forum?id=RyAl60VhTcG}
}

@article{autorl:afshar2022,
	title={Automated reinforcement learning: An overview},
	author={Afshar, Reza Refaei and Zhang, Yingqian and Vanschoren, Joaquin and Kaymak, Uzay},
	journal={arXiv preprint},
	year={2022}
}

% -------------------------

@inproceedings{hardt2016,
	title={Train faster, generalize better: Stability of stochastic gradient descent},
	author={Hardt, Moritz and Recht, Ben and Singer, Yoram},
	booktitle={International conference on machine learning},
	pages={1225--1234},
	year={2016},
	organization={PMLR}
}
@article{song2019,
	title={Observational overfitting in reinforcement learning},
	author={Song, Xingyou and Jiang, Yiding and Tu, Stephen and Du, Yilun and Neyshabur, Behnam},
	journal={arXiv preprint arXiv:1912.02975},
	year={2019}
}

% -------------------------------------------------------------------------------------------------
% REINFORCE convergence issues
% -------------------------------------------------------------------------------------------------
@inproceedings{zhang2021sample,
	title={Sample efficient reinforcement learning with REINFORCE},
	author={Zhang, Junzi and Kim, Jongho and O'Donoghue, Brendan and Boyd, Stephen},
	booktitle={Proceedings of the AAAI conference on artificial intelligence},
	volume={35},
	number={12},
	pages={10887--10895},
	year={2021}
}
@article{zhang2021convergence,
	title={On the convergence and sample efficiency of variance-reduced policy gradient method},
	author={Zhang, Junyu and Ni, Chengzhuo and Szepesvari, Csaba and Wang, Mengdi and others},
	journal={Advances in Neural Information Processing Systems},
	volume={34},
	pages={2228--2240},
	year={2021}
}
@article{peck2019,
	title={A Review of REINFORCE Algorithms},
	author={Peck, Ryan and Renaux, Louis},
	year={2019}
}
% -------------------------------------------------------------------------------------------------
% AutoML
% -------------------------------------------------------------------------------------------------
@article{AutoML-Hadi,
	Author = {Hadi, Russul H. and Hady, Haider N. and Hasan, Ahmed M. and Al-Jodah,
	Ammar and Humaidi, Amjad J.},
	Title = {Improved Fault Classification for Predictive Maintenance in Industrial IoT Based on AutoML: A Case Study of Ball-Bearing Faults},
	Journal = {PROCESSES},
	Year = {2023},
	Volume = {11},
	Number = {5},
	Month = {MAY 15},
	DOI = {10.3390/pr11051507},
	Article-Number = {1507},
}

@article{AutoML-Maurer,
	Author = {Maurer, Matthias and Festl, Andreas and Bricelj, Bor and Schneider,
	Germar and Schmeja, Michael},
	Title = {AutoML for Log File Analysis (ALFA) in a Production Line System of
	Systems pointed towards Predictive Maintenance},
	Journal = {INFOCOMMUNICATIONS JOURNAL},
	Year = {2021},
	Volume = {13},
	Number = {3},
	Pages = {76-84},
	Month = {SEP},
	DOI = {10.36244/ICJ.2021.3.8},
}

@incollection{AutoML-Tornede,
	Author = {Tornede, Tanja and Tornede, Alexander and Wever, Marcel and
	Huellermeier, Eyke},
	Book-Group-Author = {ACM},
	Title = {Coevolution of Remaining Useful Lifetime Estimation Pipelines for
	Automated Predictive Maintenance},
	Booktitle = {PROCEEDINGS OF THE 2021 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE
	(GECCO'21)},
	Year = {2021},
	Pages = {368-376},
	DOI = {10.1145/3449639.3459395},
	Keywords = {Coevolution; AutoML; Predictive Maintenance; Remaining Useful Lifetime},
	Unique-ID = {WOS:000773791800045},
}

@article{AutoML-Cinar,
	Author = {Cinar, Eyup and Kalay, Sena and Saricicek, Inci},
	Title = {A Predictive Maintenance System Design and Implementation for
	Intelligent Manufacturing},
	Journal = {MACHINES},
	Year = {2022},
	Volume = {10},
	Number = {11},
	Month = {OCT 31},
	DOI = {10.3390/machines10111006},
	Article-Number = {1006},
	Keywords = {automated machine learning (AutoML); cyber-physical systems (CPSs); data
	augmentation; key performance indicators (KPIs); predictive maintenance
	(PdM)},
	Unique-ID = {WOS:000908038000001},
}

@article{AutoML-Ferreira,
	Author = {Ferreira, Luis and Pilastri, Andre and Romano, Filipe and Cortez, Paulo},
	Title = {Using supervised and one-class automated machine learning for predictive
	maintenance},
	Journal = {APPLIED SOFT COMPUTING},
	Year = {2022},
	Volume = {131},
	Month = {DEC},
	DOI = {10.1016/j.asoc.2022.109820},
	EarlyAccessDate = {NOV 2022},
	Article-Number = {109820},
	Keywords = {Automated machine learning; Predictive maintenance; Supervised learning;
	One -class learning},
	Keywords-Plus = {EFFICIENT},
	Unique-ID = {WOS:000895447300004},
}

@incollection{AutoML-Larocque,
	Author = {Larocque-Villiers, Justin and Dumond, Patrick and Knox, David},
	Book-Group-Author = {IEEE},
	Title = {Automating Predictive Maintenance Using State-Based Transfer Learning
	and Ensemble Methods},
	Booktitle = {2021 IEEE INTERNATIONAL SYMPOSIUM ON ROBOTIC AND SENSORS ENVIRONMENTS
	(ROSE 2021)},
	Year = {2021},
	DOI = {10.1109/ROSE52750.2021.9611768},
	Keywords = {AutoML; Unsupervised Learning; Signal Processing; Transfer Learning;
	Meta-Learning; Ensemble Learning},
	Unique-ID = {WOS:000784140000011},
}

@incollection{AutoML-Rivas,
	Author = {Rivas, Jannery and Boya-Lara, Carlos and Poveda, Hector},
	Book-Group-Author = {IEEE},
	Title = {Partial discharge detection in power lines using automated machine
	learning},
	Booktitle = {2022 8TH INTERNATIONAL ENGINEERING, SCIENCES AND TECHNOLOGY CONFERENCE,
	IESTEC},
	Year = {2022},
	Pages = {223-230},
	DOI = {10.1109/IESTEC54539.2022.00041},
	Keywords = {partial discharge; detection; machine learning; AutoML; power lines},
	Keywords-Plus = {IDENTIFICATION; CLASSIFICATION},
	Unique-ID = {WOS:000986616400032},
}

@article{AutoML-Zarate,
	Author = {Enriquez Zarate, Josue and Gomez Lopez, Maria de los Angeles and Carmona
	Troyo, Javier Alberto and Trujillo, Leonardo},
	Title = {Analysis and Detection of Erosion in Wind Turbine Blades},
	Journal = {MATHEMATICAL AND COMPUTATIONAL APPLICATIONS},
	Year = {2022},
	Volume = {27},
	Number = {1},
	Month = {FEB},
	DOI = {10.3390/mca27010005},
	Article-Number = {5},
	Keywords = {wind energy; wind turbine blades; erosion; modal analysis; aerodynamic
	analysis; AutoML},
	Unique-ID = {WOS:000762715100001},
}

@article{AutoML-Garouani,
	Author = {Garouani, Moncef and Ahmad, Adeel and Bouneffa, Mourad and Hamlich,
	Mohamed and Bourguin, Gregory and Lewandowski, Arnaud},
	Title = {Towards big industrial data mining through explainable automated machine
	learning},
	Journal = {INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY},
	Year = {2022},
	Volume = {120},
	Number = {1-2},
	Pages = {1169-1188},
	Month = {MAY},
	DOI = {10.1007/s00170-022-08761-9},
	EarlyAccessDate = {FEB 2022},
	Keywords = {Machine learning; AutoML; Explainable AI; Data analysis;
	Decision-support systems; Industry 4; 0},
	Keywords-Plus = {HYPERPARAMETER OPTIMIZATION},
	Unique-ID = {WOS:000753286400002},
}

% -------------------------------------------------------------------------------------------------

@misc{Krishna2020,
	author        = {Velivela, Krishna and Yarram, Sudhir},
	title         = {Comparison of Reinforcement Learning Algorithms},
	month         = {Dec},
	year          = {2020},
	publisher={Department of Computer Science and Engineering, University at Buffalo}
}

@inproceedings{sandeep2022experimental,
	title={Experimental Evaluation of Reinforcement Learning Algorithms},
	author={Sandeep Varma, N and Sinha, Vaishnavi and Pradyumna Rahul, K},
	booktitle={International Conference on Computational Intelligence and Data Engineering},
	pages={469--484},
	year={2022},
	organization={Springer}
}
@inproceedings{ford2022cognitive,
	title={Cognitive radar mode control: a comparison of different reinforcement learning algorithms},
	author={Ford, SA and Ritchie, M},
	booktitle={International Conference on Radar Systems (RADAR 2022)},
	volume={2022},
	pages={107--112},
	year={2022},
	organization={IET}
}

@article{dulac2021,
	title={Challenges of real-world reinforcement learning: definitions, benchmarks and analysis},
	author={Dulac-Arnold, Gabriel and Levine, Nir and Mankowitz, Daniel J and Li, Jerry and Paduraru, Cosmin and Gowal, Sven and Hester, Todd},
	journal={Machine Learning},
	volume={110},
	number={9},
	pages={2419--2468},
	year={2021},
	publisher={Springer}
}

@inproceedings{henderson2018deep,
	title={Deep Reinforcement Learning that Matters},
	author={Henderson, Peter and Islam, Riashat and Bachman, Philip and Pineau, Joelle and Precup, Doina and Meger, David},
	booktitle={Proceedings of the AAAI conference on artificial intelligence},
	volume={32},
	number={1},
	year={2018}
}
@inproceedings{duan2016benchmarking,
	title={Benchmarking deep reinforcement learning for continuous control},
	author={Duan, Yan and Chen, Xi and Houthooft, Rein and Schulman, John and Abbeel, Pieter},
	booktitle={International conference on machine learning},
	pages={1329--1338},
	year={2016},
	organization={PMLR}
}

@article{dulac2020empirical,
	title={An empirical investigation of the challenges of real-world reinforcement learning},
	author={Dulac-Arnold, Gabriel and Levine, Nir and Mankowitz, Daniel J and Li, Jerry and Paduraru, Cosmin and Gowal, Sven and Hester, Todd},
	journal={arXiv preprint arXiv:2003.11881},
	year={2020}
}

@article{dasic2006,
	title={Analysis of Wear Cutting Tools by Complex Power-Exponential Function for Finishing Turning of the Hardened Steel 20crmo5 by Mixed Ceramic Tools},
	author={Da{\v{s}}i{\'c}, Predrag},
	journal={Fascicle VIII Tribology},
	volume={12},
	pages={54--60},
	year={2006}
}

@book{graesser2019,
	title={Foundations of deep reinforcement learning},
	author={Graesser, Laura and Keng, Wah Loon},
	year={2019},
	publisher={Addison-Wesley Professional}
}

@article{mnih2015DQN,
  title={Human-level control through deep reinforcement learning},
  author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Rusu, Andrei A and Veness, Joel and Bellemare, Marc G and Graves, Alex and Riedmiller, Martin and Fidjeland, Andreas K and Ostrovski, Georg and others},
  journal={nature},
  volume={518},
  number={7540},
  pages={529--533},
  year={2015},
  publisher={Nature Publishing Group}
}

@inproceedings{riedmiller2005neural,
	title={Neural fitted Q iteration--first experiences with a data efficient neural reinforcement learning method},
	author={Riedmiller, Martin},
	booktitle={Machine Learning: ECML 2005: 16th European Conference on Machine Learning, Porto, Portugal, October 3-7, 2005. Proceedings 16},
	pages={317--328},
	year={2005},
	organization={Springer}
}

@misc{OpenAI-baselines,
	author = {Dhariwal, Prafulla and Hesse, Christopher and Klimov, Oleg and Nichol, Alex and Plappert, Matthias and Radford, Alec and Schulman, John and Sidor, Szymon and Wu, Yuhuai and Zhokhov, Peter},
	title = {OpenAI Baselines},
	year = {2017},
	publisher = {GitHub},
	journal = {GitHub repository},
	howpublished = {\url{https://github.com/openai/baselines}},
}

@article{REINFORCE-williams1992,
	title={Simple statistical gradient-following algorithms for connectionist reinforcement learning},
	author={Williams, Ronald J},
	journal={Reinforcement learning},
	pages={5--32},
	year={1992},
	publisher={Springer}
}

@inproceedings{A2C-mnih2016,
	title={Asynchronous methods for deep reinforcement learning},
	author={Mnih, Volodymyr and Badia, Adria Puigdomenech and Mirza, Mehdi and Graves, Alex and Lillicrap, Timothy and Harley, Tim and Silver, David and Kavukcuoglu, Koray},
	booktitle={International conference on machine learning},
	pages={1928--1937},
	year={2016},
	organization={PMLR}
}

@inproceedings{TRPO-schulman2015,
	title={Trust region policy optimization},
	author={Schulman, John and Levine, Sergey and Abbeel, Pieter and Jordan, Michael and Moritz, Philipp},
	booktitle={International conference on machine learning},
	pages={1889--1897},
	year={2015},
	organization={PMLR}
}

@article{DQN-mnih2013,
	title={Playing atari with deep reinforcement learning},
	author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Graves, Alex and Antonoglou, Ioannis and Wierstra, Daan and Riedmiller, Martin},
	journal={arXiv preprint arXiv:1312.5602},
	year={2013}
}
@article{PPO-schulman2017,
	title={Proximal policy optimization algorithms},
	author={Schulman, John and Wolski, Filip and Dhariwal, Prafulla and Radford, Alec and Klimov, Oleg},
	journal={arXiv preprint arXiv:1707.06347},
	year={2017}
}

@book{barto2018,
	author={Richard Sutton and Andrew Barto},
	year={2018},
	title={Reinforcement Learning: An Introduction},
	publisher={The MIT Press},
	address={Cambridge, England},
	edition={2nd. edition}
}

@misc{PHM-dataset,
	doi = {10.21227/jdxd-yy51},
	url = {https://dx.doi.org/10.21227/jdxd-yy51},
	author = {Li, Xinghui},
	publisher = {IEEE Dataport},
	title = {2010 PHM Society Conference Data Challenge},
	year = {2021}
}
	
@misc{NUAA-dataset,
	doi = {10.21227/3aa1-5e83},
	url = {https://dx.doi.org/10.21227/3aa1-5e83},
	author = {Yingguang, LI and Changqing, LIU and Dehua, LI and Jiaqi, HUA and Peng, WAN},
	publisher = {IEEE Dataport},
	title = {Tool wear dataset of NUAA Ideahouse},
	year = {2021}}


@inproceedings{dai2021reinforcement,
	title={Reinforcement lion swarm optimization algorithm for tool wear prediction},
	author={Dai, Zixiang and Jiang, Mingyan and Li, Xiaogang and Yuan, Dongfeng and Zhou, Xiaotian},
	booktitle={2021 Global Reliability and Prognostics and Health Management (PHM-Nanjing)},
	pages={1--7},
	year={2021},
	organization={IEEE}
}

@article{oshida2023development,
	title={Development and implementation of real-time anomaly detection on tool wear based on stacked LSTM encoder-decoder model},
	author={Oshida, Taisuke and Murakoshi, Tomohiro and Zhou, Libo and Ojima, Hirotaka and Kaneko, Kazuki and Onuki, Teppei and Shimizu, Jun},
	journal={The International Journal of Advanced Manufacturing Technology},
	pages={1--16},
	year={2023},
	publisher={Springer}
}

# Brian Duignan - Britannica
@misc{occams-razor,
	author = {Britannica}, 
	year = {2022},
	title = {Occam's razor},
	url = {https://www.britannica.com/topic/Occams-razor},
	publisher = {Encyclopaedia Britannica},
	note = {Accessed: 2023-06-23}
}

@misc{milling-market,
	author = {{Future Market Insights}},
	year = {2023},
	month = {1},
	title = {Milling Machine Market Outlook (2023 to 2033)},
	url = {https://www.futuremarketinsights.com/reports/milling-machine-market},
	publisher = {Future Market Insights, Inc.},
	note = {Accessed: 2023-06-23}
}


@article{SB3-paper,
	author = {Raffin, Antonin and Hill, Ashley and Gleave, Adam and Kanervisto, Anssi and Ernestus, Maximilian and Dormann, Noah},
	title = {Stable-Baselines3: Reliable Reinforcement Learning Implementations},
	year = {2021},
	issue_date = {January 2021},
	publisher = {JMLR.org},
	volume = {22},
	number = {1},
	issn = {1532-4435},
	journal = {J. Mach. Learn. Res.},
	month = {jan},
	articleno = {268},
	numpages = {8},
}
@misc{SB3-algorithms,
	title = {Stable-Baselines3 - Master list of algorithms},
	author = {{SB3-Algorithms}},
	year={2022},
	url = {https://stable-baselines3.readthedocs.io/en/master/guide/algos.html},
	note = {Accessed: 2023-06-27}
}

@misc{SB3-home,
	title = {Stable-Baselines3 Docs - Reliable Reinforcement Learning Implementations},
	url = {https://stable-baselines3.readthedocs.io/en/master/index.html},
	note = {Accessed: 2023-05-14},
}

@misc{SB3-DefaultNetwork,
	title = {Stable-Baselines3 - Default Network Architecture},
	author = {{SB3-Default Network Architecture}},
	year={2022},
	url = {https://stable-baselines3.readthedocs.io/en/master/guide/custom_policy.html#default-network-architecture},
	note = {Accessed: 2023-06-27}
}

@article{SB3-PPO-implementation,
	author = {Huang, Shengyi; Dossa, Rousslan Fernand Julien; Raffin, Antonin; Kanervisto, Anssi; Wang, Weixun},
	title = {The 37 Implementation Details of Proximal Policy Optimization},
	year = {2022},
	month = {March},
	day = {25},
	publisher = {},	
	note = {Accessed: 2023-06-27}
}

@article{siraskar2023,
	title={Reinforcement learning for predictive maintenance: a systematic technical review},
	author={Siraskar, Rajesh and Kumar, Satish and Patil, Shruti and Bongale, Arunkumar and Kotecha, Ketan},
	journal={Artificial Intelligence Review},
	pages={1--63},
	year={2023},
	publisher={Springer}
}

% Scopus - ML for milling machine predictive maintenance

@ARTICLE{Twardowski2023,
	author = {Twardowski, Paweł and Czyżycki, Jakub and Felusiak-Czyryca, Agata and Tabaszewski, Maciej and Wiciak-Pikuła, Martyna},
	title = {Monitoring and forecasting of tool wear based on measurements of vibration accelerations during cast iron milling},
	year = {2023},
	journal = {Journal of Manufacturing Processes},
	volume = {95},
	pages = {342 – 350},
	doi = {10.1016/j.jmapro.2023.04.036},
}

@ARTICLE{Denkena2023,
	author = {Denkena, Berend and Klemme, Heinrich and Stiehl, Tobias H.},
	title = {Tool Wear Monitoring Using Process Data of Multiple Machine Tools by Means of Machine Learning},
	year = {2023},
	journal = {ZWF Zeitschrift fuer Wirtschaftlichen Fabrikbetrieb},
	volume = {118},
	number = {5},
	pages = {298 – 301},
	doi = {10.1515/zwf-2023-1059},
}

@ARTICLE{Qin2023,
	author = {Qin, Bo and Wang, Yongqing and Liu, Kuo and Jiang, Shaowei and Luo, Qi},
	title = {A novel online tool condition monitoring method for milling titanium alloy with consideration of tool wear law},
	year = {2023},
	journal = {Mechanical Systems and Signal Processing},
	volume = {199},
	doi = {10.1016/j.ymssp.2023.110467},
}

@ARTICLE{Qiang2023,
	author = {Qiang, Biyao and Shi, Kaining and Liu, Ning and Ren, Junxue and Shi, Yaoyao},
	title = {Integrating physics-informed recurrent Gaussian process regression into instance transfer for predicting tool wear in milling process},
	year = {2023},
	journal = {Journal of Manufacturing Systems},
	volume = {68},
	pages = {42 – 55},
	doi = {10.1016/j.jmsy.2023.02.019},
}

@ARTICLE{Panzer2021,
	title={Deep reinforcement learning in production systems: a systematic literature review},
	author={Panzer, Marcel and Bender, Benedict},
	journal={International Journal of Production Research},
	year={2021},
	publisher={Taylor and Francis}
}

@ARTICLE{Erhan2021,
	author={Erhan, L. and Ndubuaku, M. and Di Mauro, M. and Song, W. and Chen, M. and Fortino, G. and Bagdasar, O. and Liotta, A.},
	title={Smart anomaly detection in sensor systems: A multi-perspective review},
	journal={Information Fusion},
	year={2021},
	volume={67},
	pages={64-79},
	doi={10.1016/j.inffus.2020.10.001},
	publisher={Elsevier B.V.},
}