{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T17:13:57Z","timestamp":1782234837297,"version":"3.54.5"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030938413","type":"print"},{"value":"9783030938420","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-93842-0_11","type":"book-chapter","created":{"date-parts":[[2022,1,11]],"date-time":"2022-01-11T18:25:30Z","timestamp":1641925530000},"page":"187-200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Transfer Learning and Curriculum Learning in Sokoban"],"prefix":"10.1007","author":[{"given":"Zhao","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mike","family":"Preuss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aske","family":"Plaat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,1,11]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, C.W., Lee, M., Elliott, D.L.: Faster reinforcement learning after pretraining deep networks to predict state dynamics. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20137. IEEE (2015)","DOI":"10.1109\/IJCNN.2015.7280824"},{"key":"11_CR2","unstructured":"Badia, A.P., et al.: Agent57: Outperforming the Atari human benchmark. In: International Conference on Machine Learning, pp. 507\u2013517. PMLR (2020)"},{"key":"11_CR3","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. arXiv preprint arXiv:2005.14165 (2020)"},{"key":"11_CR4","unstructured":"Brys, T., Harutyunyan, A., Taylor, M.E., Now\u00e9, A.: Policy transfer using reward shaping. In: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems, pp. 181\u2013188 (2015)"},{"key":"11_CR5","doi-asserted-by":"publisher","unstructured":"Cook, M., Raad, A.: Hyperstate space graphs for automated game analysis. In: IEEE Conference on Games, CoG 2019, London, United Kingdom, 20\u201323 August 2019, pp. 1\u20138. IEEE (2019). https:\/\/doi.org\/10.1109\/CIG.2019.8848026","DOI":"10.1109\/CIG.2019.8848026"},{"key":"11_CR6","unstructured":"De la Cruz, G., Du, Y., Irwin, J., Taylor, M.: Initial progress in transfer for deep reinforcement learning algorithms. In: 25th International Joint Conference on Artificial Intelligence (IJCAI), vol. 7 (2016)"},{"key":"11_CR7","unstructured":"Cruz, G.V., Jr., Du, Y., Taylor, M.E.: Pre-training neural networks with human demonstrations for deep reinforcement learning. arXiv preprint arXiv:1709.04083 (2017)"},{"key":"11_CR8","unstructured":"Culberson, J.: Sokoban is PSPACE-complete (1997)"},{"key":"11_CR9","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"issue":"4","key":"11_CR10","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/S0925-7721(99)00017-6","volume":"13","author":"D Dor","year":"1999","unstructured":"Dor, D., Zwick, U.: Sokoban and other motion planning problems. Comput. Geom. 13(4), 215\u2013228 (1999)","journal-title":"Comput. Geom."},{"key":"11_CR11","first-page":"3141","volume":"33","author":"D Feng","year":"2020","unstructured":"Feng, D., Gomes, C.P., Selman, B.: A novel automated curriculum strategy to solve hard Sokoban planning instances. Adv. Neural. Inf. Process. Syst. 33, 3141\u20133152 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Feng, D., Gomes, C.P., Selman, B.: Solving hard AI planning instances using curriculum-driven deep reinforcement learning. CoRR abs\/2006.02689 (2020). https:\/\/arxiv.org\/abs\/2006.02689","DOI":"10.24963\/ijcai.2020\/304"},{"issue":"7","key":"11_CR13","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1016\/j.robot.2010.03.007","volume":"58","author":"F Fern\u00e1ndez","year":"2010","unstructured":"Fern\u00e1ndez, F., Garc\u00eda, J., Veloso, M.: Probabilistic policy reuse for inter-task transfer learning. Robot. Auton. Syst. 58(7), 866\u2013871 (2010)","journal-title":"Robot. Auton. Syst."},{"key":"11_CR14","unstructured":"Guez, A., et al.: An investigation of model-free planning. In: International Conference on Machine Learning, pp. 2464\u20132473. PMLR (2019)"},{"key":"11_CR15","unstructured":"Guez, A., et al.: Learning to search with MCTSnets. In: International Conference on Machine Learning, pp. 1822\u20131831. PMLR (2018)"},{"key":"11_CR16","unstructured":"Hamrick, J.B., et al.: On the role of planning in model-based deep reinforcement learning. In: 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, 3\u20137 May 2021 (2021)"},{"key":"11_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11_CR18","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937. PMLR (2016)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Nair, A., McGrew, B., Andrychowicz, M., Zaremba, W., Abbeel, P.: Overcoming exploration in reinforcement learning with demonstrations. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 6292\u20136299. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8463162"},{"issue":"4","key":"11_CR20","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1109\/TCIAIG.2013.2286295","volume":"5","author":"S Ontan\u00f3n","year":"2013","unstructured":"Ontan\u00f3n, S., Synnaeve, G., Uriarte, A., Richoux, F., Churchill, D., Preuss, M.: A survey of real-time strategy game AI research and competition in StarCraft. IEEE Trans. Comput. Intell. AI Games 5(4), 293\u2013311 (2013)","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Plaat, A.: Learning to Play: Reinforcement Learning and Games. Springer, Heidelberg (2020). https:\/\/learningtoplay.net","DOI":"10.1007\/978-3-030-59238-7"},{"key":"11_CR22","unstructured":"Racani\u00e8re, S., et al.: Imagination-augmented agents for deep reinforcement learning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 5694\u20135705 (2017)"},{"key":"11_CR23","unstructured":"Schrader, M.P.B.: Gym-Sokoban (2018). https:\/\/github.com\/mpSchrader\/gym-sokoban"},{"issue":"7676","key":"11_CR24","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"key":"11_CR25","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"11_CR26","unstructured":"Spector, B., Belongie, S.: Sample-efficient reinforcement learning through transfer and architectural priors. arXiv preprint arXiv:1801.02268 (2018)"},{"key":"11_CR27","volume-title":"Reinforcement Learning, An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning, An Introduction, 2nd edn. MIT Press, Cambridge (2018)","edition":"2"},{"key":"11_CR28","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res. 10, 1633\u20131685 (2009)","journal-title":"J. Mach. Learn. Res."},{"issue":"7782","key":"11_CR29","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Xu, W., He, J., Shu, Y.: Transfer learning and deep domain adaptation. In: Advances in Deep Learning. IntechOpen (2020)","DOI":"10.5772\/intechopen.94072"},{"key":"11_CR31","unstructured":"Yosinski, J., Clune, J., Bengio, Y., Lipson, H.: How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, pp. 3320\u20133328 (2014)"}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence and Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-93842-0_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,29]],"date-time":"2022-04-29T06:33:46Z","timestamp":1651214026000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-93842-0_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030938413","9783030938420"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-93842-0_11","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"11 January 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BNAIC\/Benelearn","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Benelux Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Esch-sur-Alzette","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Luxembourg","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bnaic2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/bnaic2021.uni.lu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"46","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"14","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"30% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}