{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:26:11Z","timestamp":1742912771248,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030661502"},{"type":"electronic","value":"9783030661519"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-66151-9_6","type":"book-chapter","created":{"date-parts":[[2020,12,21]],"date-time":"2020-12-21T00:02:47Z","timestamp":1608508967000},"page":"85-100","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning to Generalise in Sparse Reward Navigation Environments"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4329-8137","authenticated-orcid":false,"given":"Asad","family":"Jeewa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7160-6972","authenticated-orcid":false,"given":"Anban W.","family":"Pillay","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1776-1925","authenticated-orcid":false,"given":"Edgar","family":"Jembere","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,12,21]]},"reference":[{"key":"6_CR1","unstructured":"Centre for high performance computing. https:\/\/www.chpc.ac.za\/"},{"key":"6_CR2","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: Advances in Neural Information Processing Systems, pp. 5048\u20135058 (2017)"},{"key":"6_CR3","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"6_CR4","doi-asserted-by":"publisher","unstructured":"Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning, ICML 2009, pp. 41\u201348. Association for Computing Machinery, Montreal (2009). https:\/\/doi.org\/10.1145\/1553374.1553380","DOI":"10.1145\/1553374.1553380"},{"key":"6_CR5","unstructured":"Burda, Y., Edwards, H., Pathak, D., Storkey, A., Darrell, T., Efros, A.A.: Large-scale study of curiosity-driven learning. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=rJNwDjAqYX"},{"key":"6_CR6","unstructured":"Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation. arXiv preprint arXiv:1810.12894 (2018)"},{"key":"6_CR7","unstructured":"Cobbe, K., Hesse, C., Hilton, J., Schulman, J.: Leveraging procedural generation to benchmark reinforcement learning. arXiv preprint arXiv:1912.01588, p. 27 (2019)"},{"key":"6_CR8","unstructured":"Cobbe, K., Klimov, O., Hesse, C., Kim, T., Schulman, J.: Quantifying generalization in reinforcement learning. arXiv preprint arXiv:1812.02341, p. 8 (2018)"},{"key":"6_CR9","unstructured":"Devlin, S.M., Kudenko, D.: Dynamic potential-based reward shaping (2012). http:\/\/eprints.whiterose.ac.uk\/75121\/"},{"key":"6_CR10","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: Benchmarking deep reinforcement learning for continuous control. In: International Conference on Machine Learning, pp. 1329\u20131338 (2016). http:\/\/proceedings.mlr.press\/v48\/duan16.html, ISSN: 1938\u20137228 Section: Machine Learning"},{"key":"6_CR11","unstructured":"Florensa, C., Held, D., Geng, X., Abbeel, P.: Automatic goal generation for reinforcement learning agents. In: International Conference on Machine Learning, pp. 1515\u20131528 (2018). http:\/\/proceedings.mlr.press\/v80\/florensa18a.html. ISSN: 1938\u20137228 Section: Machine Learning"},{"key":"6_CR12","unstructured":"Florensa, C., Held, D., Wulfmeier, M., Zhang, M., Abbeel, P.: Reverse curriculum generation for reinforcement learning. arXiv:1707.05300 [cs] (2018)"},{"key":"6_CR13","unstructured":"Frans, K., Ho, J., Chen, X., Abbeel, P., Schulman, J.: Meta learning shared hierarchies. arXiv:1710.09767 [cs] (2017)"},{"key":"6_CR14","unstructured":"Hacohen, G., Weinshall, D.: On the power of curriculum learning in training deep networks. arXiv:1904.03626 [cs, stat] (2019)"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Hussein, A., Elyan, E., Gaber, M.M., Jayne, C.: Deep reward shaping from demonstrations. In: Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), pp. 510\u2013517. IEEE (2017)","DOI":"10.1109\/IJCNN.2017.7965896"},{"key":"6_CR16","unstructured":"Jeewa, A., Pillay, A., Jembere, E.: Directed curiosity-driven exploration in hard exploration, sparse reward environments. In: Davel, M.H., Barnard, E. (eds.) Proceedings of the South African Forum for Artificial Intelligence Research, Cape Town, South Africa, 4\u20136 December 2019, CEUR Workshop Proceedings, vol. 2540, pp. 12\u201324. CEUR-WS.org (2019). http:\/\/ceur-ws.org\/Vol-2540\/FAIR2019_paper_42.pdf"},{"key":"6_CR17","unstructured":"Jiang, L., Meng, D., Zhao, Q., Shan, S., Hauptmann, A.G.: Self-paced curriculum learning. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (2015). https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI15\/paper\/view\/9750"},{"key":"6_CR18","unstructured":"Juliani, A., et al.: Unity: a general platform for intelligent agents. arXiv:1809.02627 [cs, stat] (2018)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Juliani, A., et al.: Obstacle tower: a generalization challenge in vision, control, and planning. arXiv:1902.01378 [cs] (2019)","DOI":"10.24963\/ijcai.2019\/373"},{"key":"6_CR20","unstructured":"Justesen, N., Torrado, R.R., Bontrager, P., Khalifa, A., Togelius, J., Risi, S.: Illuminating generalization in deep reinforcement learning through procedural level generation. arXiv:1806.10729 [cs, stat] (2018)"},{"key":"6_CR21","unstructured":"Kang, B., Jie, Z., Feng, J.: Policy optimization with demonstrations. In: International Conference on Machine Learning, pp. 2469\u20132478 (2018). http:\/\/proceedings.mlr.press\/v80\/kang18a.html"},{"key":"6_CR22","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1007\/978-3-642-30353-1_31","volume-title":"Advances in Artificial Intelligence","author":"A Karpathy","year":"2012","unstructured":"Karpathy, A., van de Panne, M.: Curriculum learning for motor skills. In: Kosseim, L., Inkpen, D. (eds.) AI 2012. LNCS (LNAI), vol. 7310, pp. 325\u2013330. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-30353-1_31"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Khalifa, A., Bontrager, P., Earle, S., Togelius, J.: PCGRL: Procedural content generation via reinforcement learning. arXiv:2001.09212 [cs, stat] (2020)","DOI":"10.1609\/aiide.v16i1.7416"},{"key":"6_CR24","doi-asserted-by":"publisher","unstructured":"Matiisen, T., Oliver, A., Cohen, T., Schulman, J.: Teacher-student curriculum learning. In: IEEE Transactions on Neural Networks and Learning Systems, pp. 1\u20139 (2019). https:\/\/doi.org\/10.1109\/TNNLS.2019.2934906","DOI":"10.1109\/TNNLS.2019.2934906"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Narvekar, S., Stone, P.: Learning curriculum policies for reinforcement learning. arXiv:1812.00285 [cs, stat] (2018)","DOI":"10.24963\/ijcai.2017\/757"},{"key":"6_CR26","first-page":"278","volume":"99","author":"AY Ng","year":"1999","unstructured":"Ng, A.Y., Harada, D., Russell, S.: Policy invariance under reward transformations: theory and application to reward shaping. ICML 99, 278\u2013287 (1999)","journal-title":"ICML"},{"key":"6_CR27","first-page":"6","volume":"1","author":"PY Oudeyer","year":"2009","unstructured":"Oudeyer, P.Y., Kaplan, F.: What is intrinsic motivation? A typology of computational approaches. Front. Neurorobotics 1, 6 (2009)","journal-title":"Front. Neurorobotics"},{"key":"6_CR28","unstructured":"Packer, C., Gao, K., Kos, J., Kr\u00e4henb\u00fchl, P., Koltun, V., Song, D.: Assessing generalization in deep reinforcement learning. arXiv:1810.12282 [cs, stat] (2019)"},{"key":"6_CR29","doi-asserted-by":"publisher","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2017), pp. 488\u2013489. IEEE, Honolulu (2017). https:\/\/doi.org\/10.1109\/CVPRW.2017.70, http:\/\/ieeexplore.ieee.org\/document\/8014804\/","DOI":"10.1109\/CVPRW.2017.70"},{"key":"6_CR30","unstructured":"Ramachandran, P., Zoph, B., Le, Q.V.: Searching for activation functions. arXiv:1710.05941 [cs] (2017)"},{"key":"6_CR31","doi-asserted-by":"publisher","unstructured":"Ravishankar, N.R., Vijayakumar, M.V.: Reinforcement learning algorithms: survey and classification. Indian J. Sci. Technol. 10(1), 1\u20138 (2017). https:\/\/doi.org\/10.17485\/ijst\/2017\/v10i1\/109385, http:\/\/www.indjst.org\/index.php\/indjst\/article\/view\/109385","DOI":"10.17485\/ijst\/2017\/v10i1\/109385"},{"key":"6_CR32","unstructured":"Savinov, N., Dosovitskiy, A., Koltun, V.: Semi-parametric topological memory for navigation. arXiv:1803.00653 [cs] (2018)"},{"key":"6_CR33","unstructured":"Savinov, N., et al.: Episodic curiosity through reachability. arXiv:1810.02274 [cs, stat] (2019)"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: POWERPLAY: training an increasingly general problem solver by continually searching for the simplest still unsolvable problem. arXiv:1112.5309 [cs] (2012)","DOI":"10.3389\/fpsyg.2013.00313"},{"key":"6_CR35","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv:1707.06347 [cs] (2017)"},{"key":"6_CR36","unstructured":"Suay, H.B., Brys, T.: Learning from demonstration for shaping through inverse reinforcement learning, p. 9 (2016)"},{"key":"6_CR37","unstructured":"Suay, H.B., Brys, T., Taylor, M.E., Chernova, S.: Reward shaping by demonstration. In: Proceedings of the Multi-Disciplinary Conference on Reinforcement Learning and Decision Making (RLDM) (2015)"},{"key":"6_CR38","volume-title":"Reinforcement Learning, Second Edition: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning, Second Edition: An Introduction. MIT Press, Cambridge (2018). google-Books-ID: uWV0DwAAQBAJ"},{"key":"6_CR39","unstructured":"Svetlik, M., Leonetti, M., Sinapov, J., Shah, R., Walker, N., Stone, P.: Automatic curriculum graph generation for reinforcement learning agents. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (2017). https:\/\/www.aaai.org\/ocs\/index.php\/AAAI\/AAAI17\/paper\/view\/14961"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Tessler, C., Givony, S., Zahavy, T., Mankowitz, D.J., Mannor, S.: A deep hierarchical approach to lifelong learning in minecraft. arXiv:1604.07255 [cs] (2016)","DOI":"10.1609\/aaai.v31i1.10744"},{"key":"6_CR41","doi-asserted-by":"crossref","unstructured":"Ye, C., Khalifa, A., Bontrager, P., Togelius, J.: Rotation, translation, and cropping for zero-shot generalization. arXiv:2001.09908 [cs, stat] (2020)","DOI":"10.1109\/CoG47356.2020.9231907"},{"key":"6_CR42","unstructured":"Zhang, C., Vinyals, O., Munos, R., Bengio, S.: A study on overfitting in deep reinforcement learning. arXiv:1804.06893 [cs, stat] (2018)"}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-66151-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T22:11:50Z","timestamp":1670451110000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-66151-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030661502","9783030661519"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-66151-9_6","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"21 December 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SACAIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Southern African Conference for Artificial Intelligence Research","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Muldersdrift","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"South Africa","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":"22 February 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 February 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"sacair2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/sacair.org.za\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"53","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":"19","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":"36% - 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":"3","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Dur to the COVID-19 pandemic SACAIR 2020 was postponed to February 2021","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}