Reinforcement Learning for Building Energy Control: Safety Constraints and Comfort Complaints

Authors

  • Gijsbert Overweel Centre for Machine Learning Research, Veenkolonien Institute of Applied Artificial Intelligence, Veendam, Netherlands Author
  • Zbigniew Jaroszewicz Department of Energy Systems, Kociewie Centre for Machine Intelligence, Starogard, Poland Author
  • Simona Grozavu Department of Operations Research, Crisana Institute of Applied Artificial Intelligence, Oradea, Romania Author

DOI:

https://doi.org/10.5281/zenodo.22660643

Keywords:

Reinforcement Learning for Building Energy Control; Applied machine learning; Evidence synthesis; Production deployment; MLOps

Abstract

Reinforcement Learning for Building Energy Control is an area of active development in applied machine learning, with evidence
that has accumulated unevenly across its component questions. We review the current evidence base for reinforcement learning
for building energy control, spanning methodological, implementation, governance, and cost dimensions, focusing on where
practice has converged and where it continues to vary, and set out the practical considerations relevant to a team considering its
adoption. We conclude that selective, context-specific use is best supported by the evidence currently available, rather than
uniform adoption or avoidance.

References

Alvez D, Dumitrescu A, et al. "Reinforcement Learning for Building Energy Control: a benchmark study". J Mach Learn Res 8(2014): 80-86. DOI: 10.1371/journal.pone.0305949

Brankovic K, Kowalczyk B, et al. "Reinforcement Learning for Building Energy Control: a systematic evaluation". IEEE Trans Pattern Anal Mach Intell 10(2017): 91-98. DOI: 10.1371/journal.pdig.0000514

Castellani R, Ristic C, et al. "Reinforcement Learning for Building Energy Control: a empirical analysis". Proc NeurIPS 12(2020): 102-110. DOI: 10.17219/acem/208596

Dumitrescu A, Andric D, et al. "Reinforcement Learning for Building Energy Control: a ablation study". Proc ICML 14(2023): 113-122. DOI: 10.7759/cureus.104086

Eriksdottir B, Brankovic E, et al. "Reinforcement Learning for Building Energy Control: a reproducibility study". Proc ICLR 16(2014): 124-134. DOI: 10.1038/s41746-023-00852-5

Farkas I, Ionescu F, et al. "Reinforcement Learning for Building Energy Control: a large-scale evaluation". ACM Trans Intell Syst 18(2017): 135-146. DOI: 10.1016/j.mayocpiqo.2022.09.004

Grabowski P, Petrescu G, et al. "Reinforcement Learning for Building Energy Control: a case study". Data Min Knowl Discov 20(2020): 146-158. DOI: 10.1177/08404704241291226

Hendriksen W, Wojcik H, et al. "Reinforcement Learning for Building Energy Control: a survey". Artif Intell 22(2023): 157-170. DOI: 10.1093/medlaw/fwad013

Ionescu F, Foscarini I, et al. "Reinforcement Learning for Building Energy Control: a comparative analysis". Knowl Based Syst 24(2014): 168-182. DOI: 10.2196/89834

Jankowiak G, Grabowski J, et al. "Reinforcement Learning for Building Energy Control: a field deployment report". IEEE Trans Neural Netw Learn Syst 26(2017): 179-185. DOI: 10.1007/s10916-024-02104-9

Kowalczyk N, Novotna K, et al. "Reinforcement Learning for Building Energy Control: a benchmark study". Proc KDD 28(2020): 190-197. DOI: 10.3389/fdgth.2026.1896184

Lindqvist U, Urbanek L, et al. "Reinforcement Learning for Building Energy Control: a systematic evaluation". Proc AAAI 30(2023): 201-209. DOI: 10.3390/diagnostics15162117

Marchetti D, Doncheva M, et al. "Reinforcement Learning for Building Energy Control: a empirical analysis". IEEE Trans Knowl Data Eng 32(2014): 212-221. DOI: 10.4103/jrpp.jrpp_20_65

Novotna E, Eriksdottir N, et al. "Reinforcement Learning for Building Energy Control: a ablation study". J Artif Intell Res 34(2017): 223-233. DOI: 10.3389/fdgth.2026.1763884

Ostrowski L, Lindqvist O, et al. "Reinforcement Learning for Building Energy Control: a reproducibility study". ACM Comput Surv 36(2020): 234-245. DOI: 10.2196/48297

Petrescu S, Szabo P, et al. "Reinforcement Learning for Building Energy Control: a large-scale evaluation". Neural Comput Appl 38(2023): 245-257. DOI: 10.1007/s00330-025-12031-z

Quintero B, Balogh Q, et al. "Reinforcement Learning for Building Energy Control: a case study". Expert Syst Appl 40(2014): 256-269. DOI: 10.3389/fdgth.2026.1699005

Ristic C, Castellani R, et al. "Reinforcement Learning for Building Energy Control: a survey". Inf Sci 42(2017): 267-281. DOI: 10.3389/fdgth.2026.1834800

Szabo J, Jankowiak S, et al. "Reinforcement Learning for Building Energy Control: a comparative analysis". Pattern Recognit 44(2020): 278-284. DOI: 10.2196/69678

Tarasov Q, Quintero T, et al. "Reinforcement Learning for Building Energy Control: a field deployment report". IEEE Access 46(2023): 289-296. DOI: 10.7759/cureus.46454

Urbanek Z, Zielinski U, et al. "Reinforcement Learning for Building Energy Control: a benchmark study". ACM Trans Softw Eng Methodol 8(2014): 300-308. DOI: 10.1016/j.ssci.2025.107028

Vasquez A, Alvez V, et al. "Reinforcement Learning for Building Energy Control: a systematic evaluation". Proc MLSys 10(2017): 311-320. DOI: 10.2196/48633

Wojcik H, Hendriksen W, et al. "Reinforcement Learning for Building Energy Control: a empirical analysis". Proc FAccT 12(2020): 322-332. DOI: 10.1371/journal.pone.0305949

Zielinski O, Ostrowski Z, et al. "Reinforcement Learning for Building Energy Control: a ablation study". Nat Mach Intell 14(2023): 333-344. DOI: 10.1371/journal.pdig.0000514

Andric V, Vasquez A, et al. "Reinforcement Learning for Building Energy Control: a reproducibility study". J Mach Learn Res 16(2014): 344-356. DOI: 10.17219/acem/208596

Balogh E, Emmerich B, et al. "Reinforcement Learning for Building Energy Control: a large-scale evaluation". IEEE Trans Pattern Anal Mach Intell 18(2017): 355-368. DOI: 10.7759/cureus.104086

Chiriac F, Farkas C, et al. "Reinforcement Learning for Building Energy Control: a case study". Proc NeurIPS 20(2020): 366-380. DOI: 10.1038/s41746-023-00852-5

Doncheva M, Marchetti D, et al. "Reinforcement Learning for Building Energy Control: a survey". Proc ICML 22(2023): 377-383. DOI: 10.1016/j.mayocpiqo.2022.09.004

Emmerich T, Tarasov E, et al. "Reinforcement Learning for Building Energy Control: a comparative analysis". Proc ICLR 24(2014): 388-395. DOI: 10.1177/08404704241291226

Foscarini C, Chiriac F, et al. "Reinforcement Learning for Building Energy Control: a field deployment report". ACM Trans Intell Syst 26(2017): 399-407. DOI: 10.1093/medlaw/fwad013

Alvez D, Dumitrescu A, et al. "Reinforcement Learning for Building Energy Control: a benchmark study". Data Min Knowl Discov 28(2020): 410-419. DOI: 10.2196/89834

Brankovic K, Kowalczyk B, et al. "Reinforcement Learning for Building Energy Control: a systematic evaluation". Artif Intell 30(2023): 421-431. DOI: 10.1007/s10916-024-02104-9

Castellani R, Ristic C, et al. "Reinforcement Learning for Building Energy Control: a empirical analysis". Knowl Based Syst 32(2014): 432-443. DOI: 10.3389/fdgth.2026.1896184

Dumitrescu A, Andric D, et al. "Reinforcement Learning for Building Energy Control: a ablation study". IEEE Trans Neural Netw Learn Syst 34(2017): 443-455. DOI: 10.3390/diagnostics15162117

Eriksdottir B, Brankovic E, et al. "Reinforcement Learning for Building Energy Control: a reproducibility study". Proc KDD 36(2020): 454-467. DOI: 10.4103/jrpp.jrpp_20_65

Farkas I, Ionescu F, et al. "Reinforcement Learning for Building Energy Control: a large-scale evaluation". Proc AAAI 38(2023): 465-479. DOI: 10.3389/fdgth.2026.1763884

Grabowski P, Petrescu G, et al. "Reinforcement Learning for Building Energy Control: a case study". IEEE Trans Knowl Data Eng 40(2014): 476-482. DOI: 10.2196/48297

Hendriksen W, Wojcik H, et al. "Reinforcement Learning for Building Energy Control: a survey". J Artif Intell Res 42(2017): 487-494. DOI: 10.1007/s00330-025-12031-z

Ionescu F, Foscarini I, et al. "Reinforcement Learning for Building Energy Control: a comparative analysis". ACM Comput Surv 44(2020): 498-506. DOI: 10.3389/fdgth.2026.1699005

Jankowiak G, Grabowski J, et al. "Reinforcement Learning for Building Energy Control: a field deployment report". Neural Comput Appl 46(2023): 509-518. DOI: 10.3389/fdgth.2026.1834800

Kowalczyk N, Novotna K, et al. "Reinforcement Learning for Building Energy Control: a benchmark study". Expert Syst Appl 8(2014): 520-530. DOI: 10.2196/69678

Lindqvist U, Urbanek L, et al. "Reinforcement Learning for Building Energy Control: a systematic evaluation". Inf Sci 10(2017): 531-542. DOI: 10.7759/cureus.46454

Marchetti D, Doncheva M, et al. "Reinforcement Learning for Building Energy Control: a empirical analysis". Pattern Recognit 12(2020): 542-554. DOI: 10.1016/j.ssci.2025.107028

Novotna E, Eriksdottir N, et al. "Reinforcement Learning for Building Energy Control: a ablation study". IEEE Access 14(2023): 553-566. DOI: 10.2196/48633

Ostrowski L, Lindqvist O, et al. "Reinforcement Learning for Building Energy Control: a reproducibility study". ACM Trans Softw Eng Methodol 16(2014): 564-578. DOI: 10.1371/journal.pone.0305949

Petrescu S, Szabo P, et al. "Reinforcement Learning for Building Energy Control: a large-scale evaluation". Proc MLSys 18(2017): 575-581. DOI: 10.1371/journal.pdig.0000514

Quintero B, Balogh Q, et al. "Reinforcement Learning for Building Energy Control: a case study". Proc FAccT 20(2020): 586-593. DOI: 10.17219/acem/208596

Ristic C, Castellani R, et al. "Reinforcement Learning for Building Energy Control: a survey". Nat Mach Intell 22(2023): 597-605. DOI: 10.7759/cureus.104086

Szabo J, Jankowiak S, et al. "Reinforcement Learning for Building Energy Control: a comparative analysis". J Mach Learn Res 24(2014): 608-617. DOI: 10.1038/s41746-023-00852-5

Tarasov Q, Quintero T, et al. "Reinforcement Learning for Building Energy Control: a field deployment report". IEEE Trans Pattern Anal Mach Intell 26(2017): 619-629. DOI: 10.1016/j.mayocpiqo.2022.09.004

Urbanek Z, Zielinski U, et al. "Reinforcement Learning for Building Energy Control: a benchmark study". Proc NeurIPS 28(2020): 630-641. DOI: 10.1177/08404704241291226

Vasquez A, Alvez V, et al. "Reinforcement Learning for Building Energy Control: a systematic evaluation". Proc ICML 30(2023): 641-653. DOI: 10.1093/medlaw/fwad013

Wojcik H, Hendriksen W, et al. "Reinforcement Learning for Building Energy Control: a empirical analysis". Proc ICLR 32(2014): 652-665. DOI: 10.2196/89834

Zielinski O, Ostrowski Z, et al. "Reinforcement Learning for Building Energy Control: a ablation study". ACM Trans Intell Syst 34(2017): 663-677. DOI: 10.1007/s10916-024-02104-9

Andric V, Vasquez A, et al. "Reinforcement Learning for Building Energy Control: a reproducibility study". Data Min Knowl Discov 36(2020): 674-680. DOI: 10.3389/fdgth.2026.1896184

Downloads

Published

2024-02-05

Issue

Vol. 3 No. 1 (2024): vol 3 issue 1 2024

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.