{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T13:16:39Z","timestamp":1775135799567,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032156372","type":"print"},{"value":"9783032156389","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-15638-9_4","type":"book-chapter","created":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T12:38:24Z","timestamp":1770727104000},"page":"50-73","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explain to\u00a0Gain: Optimising Performance Through Explainable Reinforcement Learning Parameter Investigation"],"prefix":"10.1007","author":[{"given":"Patrick","family":"Capaldo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Varniethan","family":"Ketheeswaran","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Santiago","family":"Quintana-Amate","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Delaney","family":"Stevens","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Hall","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,11]]},"reference":[{"key":"4_CR1","doi-asserted-by":"publisher","unstructured":"Ayyar, M., Benois-Pineau, J., Zemmari, A.: Esl: explain to improve streaming learning for transformers. In: International Conference on Pattern Recognition, pp. 160\u2013175. Springer (2025). https:\/\/doi.org\/10.1007\/978-3-031-78189-6_11","DOI":"10.1007\/978-3-031-78189-6_11"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Wu, X., Yu, J., Sun, W., Guo, W., Xing, X.: Statemask: explaining deep reinforcement learning through state mask. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-2728"},{"key":"4_CR3","unstructured":"Cheng, Z., Wu, X., Yu, J., Yang, S., Wang, G., Xing, X.: Rice: breaking through the training bottlenecks of reinforcement learning with explanation. arXiv preprint arXiv:2405.03064 (2024)"},{"key":"4_CR4","unstructured":"Cheng, Z., Wu, X., Yu, J., Yang, S., Wang, G., Xing, X.: Rice: breaking through the training bottlenecks of reinforcement learning with explanation. In: International Conference on Machine Learning (2024)"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Devlin, S.M., Kudenko, D.: Dynamic potential-based reward shaping. In: International Conference on Autonomous Agents and Multiagent Systems, pp. 433\u2013440 (2012)","DOI":"10.65109\/JJTT8551"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Finkelstein, M., Liu, L., Schlot, N., Kolumbus, Y., Parkes, D., Rosenschein, J., Keren, S.: Explainable reinforcement learning via model transforms. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 12943\u201312944 (2022)","DOI":"10.1609\/aaai.v36i11.21608"},{"key":"4_CR7","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"4_CR8","unstructured":"Guo, W., Wu, X., Khan, U., Xing, X.: Edge: explaining deep reinforcement learning policies. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 12222\u201312236 (2021)"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, A., Pacchiano, A., Zhai, Y., Kakade, S., Levine, S.: Unpacking reward shaping: Understanding the benefits of reward engineering on sample complexity. In: Advances in Neural Information Processing Systems, vol.\u00a035, pp. 15281\u201315295 (2022)","DOI":"10.52202\/068431-1112"},{"key":"4_CR10","unstructured":"He, C., Nachum, O., Theocharous, G., Campbell, M.: Explainable reinforcement learning via model transforms. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS), vol.\u00a035, pp. 12345\u201312358 (2022)"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Heuillet, A., Couthouis, F., Daz-Rodriguez, N.: Explainability in deep reinforcement learning. Knowledge-Based Syst. (2021)","DOI":"10.1016\/j.knosys.2020.106685"},{"key":"4_CR12","unstructured":"Hu, Y., et al.: Learning to utilize shaping rewards: a new approach of reward shaping. In: Advances in Neural Information Processing Systems, vol.\u00a033, pp. 15931\u201315941 (2020)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Jacq, A., Ferret, J., Pietquin, O., Geist, M.: Lazy-mdps: towards interpretable rl by learning when to act. In: International Conference on Autonomous Agents and Multiagent Systems, pp. 669\u2013677 (2022)","DOI":"10.65109\/LSJA4953"},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Jia, Y., Mcdermid, J., Lawton, T., Habli, I.: The role of explainability in assuring safety of machine learning in healthcare. IEEE Trans. Emerging Topics Comput. 10, 1746\u20131760 (2021). https:\/\/api.semanticscholar.org\/CorpusID:237385754","DOI":"10.1109\/TETC.2022.3171314"},{"key":"4_CR15","unstructured":"Jiang, Z., et\u00a0al.: Reinforcement learning from imperfect corrective actions and proxy rewards. arXiv preprint arXiv:2410.05782 (2024)"},{"key":"4_CR16","unstructured":"Liu, S., Zhu, M.: Utility: utilizing explainable reinforcement learning to improve reinforcement learning. In: The Thirteenth International Conference on Learning Representations (2025)"},{"key":"4_CR17","unstructured":"Lu, W., Zhao, X., Fryen, T., Lee, J., Li, M., Magg, S., Wermter, S.: Causal state distillation for explainable reinforcement learning. In: 3rd Conference on Causal Learning and Reasoning (CLeaR) (2024)"},{"issue":"35","key":"4_CR18","doi-asserted-by":"publisher","first-page":"83339","DOI":"10.1007\/s11042-024-18687-x","volume":"83","author":"R Mallic","year":"2024","unstructured":"Mallic, R., et al.: A hybrid transformer with domain adaptation using interpretability techniques for the application to the detection of risk situations. Multimedia Tools Appli. 83(35), 83339\u201383356 (2024)","journal-title":"Multimedia Tools Appli."},{"issue":"1","key":"4_CR19","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1111\/j.0030-1299.2004.13110.x","volume":"107","author":"C Mulder","year":"2004","unstructured":"Mulder, C., Bazeley-White, E., Dimitrakopoulos, P., Hector, A., Scherer-Lorenzen, M., Schmid, B.: Species evenness and productivity in experimental plant communities. Oikos 107(1), 50\u201363 (2004)","journal-title":"Oikos"},{"key":"4_CR20","unstructured":"Ng, A.Y., Harada, D., Russell, S.J.: Policy invariance under reward transformations: theory and application to reward shaping. In: International Conference on Machine Learning, pp. 278\u2013287 (1999)"},{"key":"4_CR21","unstructured":"Ng, A., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. In: International Conference on Machine Learning, pp. 278\u2013287 (1999)"},{"key":"4_CR22","unstructured":"Oh, J., Guo, Y., Singh, S., Lee, H.: Self-imitation learning. In: International Conference on Machine Learning, pp. 3878\u20133887 (2018)"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Puiutta, E., Veith, E.: Explainable reinforcement learning: a survey, pp. 77\u201395 (2020)","DOI":"10.1007\/978-3-030-57321-8_5"},{"key":"4_CR24","doi-asserted-by":"publisher","unstructured":"Quintana-Amate, S., Stevens, D., ketheeswaran, V., Capaldo, P., Sheldon, D., Hall, M.: Explain to gain: Introspective reinforcement learning for enhanced performance. In: Communications in Computer and Information Science, vol.\u00a030. Springer (2025). https:\/\/doi.org\/10.1007\/978-3-032-08324-1_11","DOI":"10.1007\/978-3-032-08324-1_11"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Retzlaff, C., et al.: Human-in-the-loop reinforcement learning: a survey and position on requirements, challenges, and opportunities. J. Artifi. Intel. Res. 79, 359\u2013415 (2024). https:\/\/api.semanticscholar.org\/CorpusID:267448673","DOI":"10.1613\/jair.1.15348"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Sequeira, P., Gervasio, M.: Interestingness elements for explainable reinforcement learning: understanding agents\u2019 capabilities and limitations. Artifi. Intell. (2020)","DOI":"10.1016\/j.artint.2020.103367"},{"key":"4_CR27","doi-asserted-by":"publisher","unstructured":"Sequeira, P., Gervasio, M.: Ixdrl: a novel explainable deep reinforcement learning toolkit based on analyses of interestingness. In: World Conference on Explainable Artificial Intelligence, pp. 373\u2013396. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-44064-9_20","DOI":"10.1007\/978-3-031-44064-9_20"},{"key":"4_CR28","unstructured":"Shicheng\u00a0Liu, M.Z.: Utility: utilizing explainable reinforcement learning to improve reinforcement learning. In: The Thirteenth International Conference on Learning Representations (2025)"},{"issue":"6419","key":"4_CR29","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362(6419), 1140\u20131144 (2018)","journal-title":"Science"},{"key":"4_CR30","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An Introduction, second edition edn.. MIT Press (2018)"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Taylor, M.E.: Improving reinforcement learning with human input. In: International Joint Conference on Artificial Intelligence, pp. 5724\u20135728 (2018)","DOI":"10.24963\/ijcai.2018\/817"},{"issue":"32","key":"4_CR32","doi-asserted-by":"publisher","first-page":"23429","DOI":"10.1007\/s00521-021-06375-y","volume":"35","author":"ME Taylor","year":"2023","unstructured":"Taylor, M.E., Nissen, N., Wang, Y., Navidi, N.: Improving reinforcement learning with human assistance: an argument for human subject studies with hippo gym. Neural Comput. Appl. 35(32), 23429\u201323439 (2023)","journal-title":"Neural Comput. Appl."},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Vinyals, O., et al.: Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","DOI":"10.1038\/s41586-019-1724-z"},{"key":"4_CR34","doi-asserted-by":"crossref","unstructured":"Wang, Z., Taylor, M.: Improving reinforcement learning with confidence-based demonstrations. In: International Joint Conference on Artificial Intelligence, pp. 3027\u20133033 (2017)","DOI":"10.24963\/ijcai.2017\/422"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Z., Taylor, M.E.: Improving reinforcement learning with confidence-based demonstrations. In: International Joint Conference on Artificial Intelligence, pp. 3027\u20133033 (2017)","DOI":"10.24963\/ijcai.2017\/422"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"van Waveren, S., Pek, C., Tumova, J., Leite, I.: Correct me if i\u2019m wrong: using non-experts to repair reinforcement learning policies. In: Proceedings of the 2022 ACM\/IEEE International Conference on Human-Robot Interaction (HRI), pp. 493\u2013501. IEEE (2022)","DOI":"10.1109\/HRI53351.2022.9889604"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Xu, M., Chen, X., Wang, J.: Policy correction and state-conditioned action evaluation for few-shot lifelong deep reinforcement learning. IEEE Trans. Neural Netw. Learn. Syst. (2024)","DOI":"10.1109\/TNNLS.2024.3385570"},{"key":"4_CR38","unstructured":"Yu, J., Guo, W., Qin, Q., Wang, G., Wang, T., Xing, X.: Airs: Explanation for deep reinforcement learning based security applications. In: Proc. of USENIX Security (2023)"}],"container-title":["Communications in Computer and Information Science","Computational Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-15638-9_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T12:23:33Z","timestamp":1775132613000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-15638-9_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032156372","9783032156389"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-15638-9_4","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"11 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IJCCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Joint Conference on Computational Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marbella","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ijcci2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ijcci.scitevents.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}