{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T18:35:29Z","timestamp":1782412529904,"version":"3.54.5"},"reference-count":59,"publisher":"Informa UK Limited","issue":"6","content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Journal of Experimental & Theoretical Artificial Intelligence"],"published-print":{"date-parts":[[2025,8,18]]},"DOI":"10.1080\/0952813x.2024.2321152","type":"journal-article","created":{"date-parts":[[2024,3,9]],"date-time":"2024-03-09T09:12:13Z","timestamp":1709975533000},"page":"987-1011","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":2,"title":["Satellite fault tolerant attitude control based on expert guided exploration of reinforcement learning agent"],"prefix":"10.1080","volume":"37","author":[{"given":"Hicham","family":"Henna","sequence":"first","affiliation":[{"name":"LAGE Laboratory, Kasdi Merbah University, Ouargla, Algeria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Houari","family":"Toubakh","sequence":"additional","affiliation":[{"name":"LAGE Laboratory, Kasdi Merbah University, Ouargla, Algeria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed Redouane","family":"Kafi","sequence":"additional","affiliation":[{"name":"LAGE Laboratory, Kasdi Merbah University, Ouargla, Algeria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00d6mer","family":"G\u00fcrsoy","sequence":"additional","affiliation":[{"name":"Control and Automation Engineer,Yildiz Technical University, Istanbul, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moamar","family":"Sayed-Mouchaweh","sequence":"additional","affiliation":[{"name":"IMT Nord-Europe, CERI SN, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Djemai","sequence":"additional","affiliation":[{"name":"INSA Hauts-de-France, LAMIH UMR CNRS, UPHF, Valenciennes, France"},{"name":"Quartz-Lab, ENSEA, Cergy, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2024,3,9]]},"reference":[{"key":"e_1_3_4_2_1","doi-asserted-by":"publisher","DOI":"10.37398\/JSR.2021.650325"},{"key":"e_1_3_4_3_1","volume-title":"Hilgard\u2019s introduction to psychology","author":"Atkinson R. L.","year":"1996","unstructured":"Atkinson, R. L., Atkinson, R. C., Smith, E. E., Bem, D. J., & Nolen-Hoeksema, S. (1996). Hilgard\u2019s introduction to psychology (12 ed.). Harcourt Brace College Publishers.","edition":"12"},{"key":"e_1_3_4_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40"},{"key":"e_1_3_4_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2020.02.017"},{"key":"e_1_3_4_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejcon.2019.06.005"},{"key":"e_1_3_4_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2021.02.037"},{"key":"e_1_3_4_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2955400"},{"key":"e_1_3_4_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.actaastro.2019.11.039"},{"key":"e_1_3_4_10_1","doi-asserted-by":"publisher","DOI":"10.1080\/0952813X.2022.2120089"},{"key":"e_1_3_4_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109241"},{"key":"e_1_3_4_12_1","first-page":"1587","volume-title":"International conference on machine learning","author":"Fujimoto S.","year":"2018","unstructured":"Fujimoto, S., Hoof, H., & Meger, D. (2018). Addressing function approximation error in actor-critic methods. International conference on machine learning, Stockholm (pp. 1587\u20131596)."},{"key":"e_1_3_4_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12555-016-0667-5"},{"key":"e_1_3_4_14_1","doi-asserted-by":"publisher","DOI":"10.2514\/1.A34841"},{"key":"e_1_3_4_15_1","doi-asserted-by":"publisher","DOI":"10.36001\/phmconf.2020.v12i1.1272"},{"key":"e_1_3_4_16_1","doi-asserted-by":"publisher","DOI":"10.36001\/phmconf.2022.v14i1.3216"},{"key":"e_1_3_4_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42064-021-0124-y"},{"key":"e_1_3_4_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2020.105706"},{"key":"e_1_3_4_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-010-9842-z"},{"key":"e_1_3_4_20_1","volume-title":"Markov decision processes with their applications","author":"Hu Q.","year":"2007","unstructured":"Hu, Q., & Yue, W. (2007). Markov decision processes with their applications. Springer Science & Business Media."},{"key":"e_1_3_4_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.actaastro.2022.07.024"},{"key":"e_1_3_4_22_1","volume-title":"Psykologi \u2013 paa biologisk Grundlag","author":"J\u00f8rgensen J.","year":"1962","unstructured":"J\u00f8rgensen, J. (1962). Psykologi \u2013 paa biologisk Grundlag. Scandinavian University Books."},{"key":"e_1_3_4_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-022-11055-6"},{"key":"e_1_3_4_24_1","first-page":"440","volume-title":"The 20th International Conference on Machine Learning (ICML-03)","author":"Laud A.","year":"2003","unstructured":"Laud, A., & DeJong, G. (2003). The influence of reward on the speed of reinforcement learning: An analysis of shaping. The 20th International Conference on Machine Learning (ICML-03), Washington, DC (pp. 440\u2013447)."},{"key":"e_1_3_4_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2019.105424"},{"key":"e_1_3_4_26_1","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00486.2014"},{"key":"e_1_3_4_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108865"},{"key":"e_1_3_4_28_1","doi-asserted-by":"publisher","DOI":"10.1007\/11840817_87"},{"key":"e_1_3_4_29_1","doi-asserted-by":"publisher","DOI":"10.3390\/s18124331"},{"key":"e_1_3_4_30_1","doi-asserted-by":"publisher","DOI":"10.3847\/2041-8213\/ab8016"},{"key":"e_1_3_4_31_1","unstructured":"Mnih V. Kavukcuoglu K. Silver D. Graves A. Antonoglou I. Wierstra D. & Riedmiller M. (2013). Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602."},{"key":"e_1_3_4_32_1","first-page":"278","volume-title":"International Conference on Machine Learning (ICML)","author":"Ng A.","year":"1999","unstructured":"Ng, A., Harada, D., & Russell, S. (1999). Policy invariance under reward transformations: Theory and application to reward shaping. International Conference on Machine Learning (ICML), Bled, Slovenia (pp. 278\u2013287)."},{"key":"e_1_3_4_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105798"},{"key":"e_1_3_4_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3119634"},{"key":"e_1_3_4_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops50388.2021.9473799"},{"key":"e_1_3_4_36_1","doi-asserted-by":"publisher","DOI":"10.1108\/IJICC-08-2020-0104"},{"key":"e_1_3_4_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2022.04.117"},{"key":"e_1_3_4_38_1","doi-asserted-by":"publisher","DOI":"10.3390\/mca27060089"},{"key":"e_1_3_4_39_1","volume-title":"Markov decision processes: Discrete stochastic dynamic programming","author":"Puterman M.","year":"2014","unstructured":"Puterman, M. (2014). Markov decision processes: Discrete stochastic dynamic programming. John Wiley & Sons."},{"key":"e_1_3_4_40_1","first-page":"463","volume-title":"15th International Conference on Machine Learning","volume":"98","author":"Randl\u00f8v J.","year":"1998","unstructured":"Randl\u00f8v, J., & Alstr\u00f8m, P. (1998). Learning to drive a bicycle using reinforcement learning and shaping. 15th International Conference on Machine Learning, Madison, Wisconsin, USA, 98, 463\u2013471."},{"key":"e_1_3_4_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isatra.2022.04.008"},{"key":"e_1_3_4_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107601"},{"key":"e_1_3_4_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.actaastro.2021.05.018"},{"key":"e_1_3_4_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109450"},{"key":"e_1_3_4_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2019.02.008"},{"key":"e_1_3_4_46_1","first-page":"387","volume-title":"International conference on machine learning","author":"Silver D.","year":"2014","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., & Riedmiller, M. (2014). Deterministic policy gradient algorithms. International conference on machine learning, Beijing, China (pp. 387\u2013395)."},{"key":"e_1_3_4_47_1","volume-title":"The behavior of organisms: An experimental analysis","author":"Skinner B. F.","year":"1938","unstructured":"Skinner, B. F. (1938). The behavior of organisms: An experimental analysis. Prentice Hall."},{"key":"e_1_3_4_48_1","volume-title":"Adaptive behavior and learning","author":"Staddon J. E.","year":"1983","unstructured":"Staddon, J. E. (1983). Adaptive behavior and learning. Cambridge University Press."},{"key":"e_1_3_4_49_1","volume-title":"Reinforcement learning, second edition: An introduction","author":"Sutton R. S.","year":"2018","unstructured":"Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning, second edition: An introduction. MIT Press."},{"key":"e_1_3_4_50_1","volume-title":"Advances in Neural Information Processing Systems (NIPS) conference","author":"Sutton R.","year":"1999","unstructured":"Sutton, R., McAllester, D., Singh, S., & Mansour, Y. (1999). Policy gradient methods for reinforcement learning with function approximation. Advances in Neural Information Processing Systems (NIPS) conference, Denver."},{"key":"e_1_3_4_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CAC48633.2019.8996860"},{"key":"e_1_3_4_52_1","doi-asserted-by":"publisher","DOI":"10.1080\/23249935.2020.1845250"},{"key":"e_1_3_4_53_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.07.073i"},{"key":"e_1_3_4_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105551"},{"key":"e_1_3_4_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2019.06.002"},{"key":"e_1_3_4_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_4_57_1","doi-asserted-by":"publisher","DOI":"10.1177\/0959651820952552"},{"key":"e_1_3_4_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/IECON49645.2022.9968880"},{"key":"e_1_3_4_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.099"},{"key":"e_1_3_4_60_1","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/8874619"}],"container-title":["Journal of Experimental & Theoretical Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/0952813X.2024.2321152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T11:25:56Z","timestamp":1754047556000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/0952813X.2024.2321152"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,9]]},"references-count":59,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,8,18]]}},"alternative-id":["10.1080\/0952813X.2024.2321152"],"URL":"https:\/\/doi.org\/10.1080\/0952813x.2024.2321152","relation":{},"ISSN":["0952-813X","1362-3079"],"issn-type":[{"value":"0952-813X","type":"print"},{"value":"1362-3079","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,9]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=teta20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=teta20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2023-07-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}