{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T11:48:04Z","timestamp":1742989684293,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031084201"},{"type":"electronic","value":"9783031084218"}],"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\/978-3-031-08421-8_29","type":"book-chapter","created":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T21:02:38Z","timestamp":1658178158000},"page":"413-428","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploration-Intensive Distractors: Two Environment Proposals and\u00a0a\u00a0Benchmarking"],"prefix":"10.1007","author":[{"given":"Jim Martin Catacora","family":"Ocana","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roberto","family":"Capobianco","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniele","family":"Nardi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,19]]},"reference":[{"key":"29_CR1","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS\u201917, Red Hook, NY, USA, pp. 5055\u20135065. Curran Associates Inc. (2017)"},{"key":"29_CR2","unstructured":"Badia, A.P., et al.: Agent57: outperforming the atari human benchmark. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event. Machine Learning Research, vol. 119, pp. 507\u2013517. PMLR (2020). http:\/\/proceedings.mlr.press\/v119\/badia20a.html"},{"key":"29_CR3","unstructured":"Badia, A.P., et al.: Never give up: learning directed exploration strategies. In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=Sye57xStvB"},{"key":"29_CR4","unstructured":"Bellemare, M.G., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS\u201916, Red Hook, NY, USA, pp. 1479\u20131487. Curran Associates Inc. (2016)"},{"key":"29_CR5","unstructured":"Burda, Y., Edwards, H., Pathak, D., Storkey, A.J., Darrell, T., Efros, A.A.: Large-scale study of curiosity-driven learning. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019. OpenReview.net (2019). https:\/\/openreview.net\/forum?id=rJNwDjAqYX"},{"key":"29_CR6","unstructured":"Burda, Y., Edwards, H., Storkey, A.J., Klimov, O.: Exploration by random network distillation. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, 6\u20139 May 2019. OpenReview.net (2019). https:\/\/openreview.net\/forum?id=H1lJJnR5Ym"},{"key":"29_CR7","unstructured":"Choi, J., et al.: Contingency-aware exploration in reinforcement learning. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=HyxGB2AcY7"},{"key":"29_CR8","unstructured":"Espeholt, L., et al.: IMPALA: scalable distributed deep-RL with importance weighted actor-learner architectures. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Machine Learning Research, 10\u201315 Jul 2018, vol. 80, pp. 1407\u20131416. PMLR (2018). http:\/\/proceedings.mlr.press\/v80\/espeholt18a.html"},{"key":"29_CR9","unstructured":"Eysenbach, B., Gupta, A., Ibarz, J., Levine, S.: Diversity is all you need: learning skills without a reward function. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=SJx63jRqFm"},{"key":"29_CR10","unstructured":"Florensa, C., Held, D., Geng, X., Abbeel, P.: Automatic goal generation for reinforcement learning agents. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Machine Learning Research, 10\u201315 July 2018, vol. 80, pp. 1515\u20131528. PMLR (2018). http:\/\/proceedings.mlr.press\/v80\/florensa18a.html"},{"key":"29_CR11","unstructured":"Florensa, C., Held, D., Wulfmeier, M., Zhang, M., Abbeel, P.: Reverse curriculum generation for reinforcement learning. In: Levine, S., Vanhoucke, V., Goldberg, K. (eds.) Proceedings of the 1st Annual Conference on Robot Learning. Machine Learning Research, 13\u201315 November 2017, vol. 78, pp. 482\u2013495. PMLR (2017). http:\/\/proceedings.mlr.press\/v78\/florensa17a.html"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Gu, S., Holly, E., Lillicrap, T.P., Levine, S.: Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 3389\u20133396 (2016)","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Haarnoja, T., Ha, S., Zhou, A., Tan, J., Tucker, G., Levine, S.: Learning to walk via deep reinforcement learning. In: Robotics: Science and Systems (2019). https:\/\/doi.org\/10.15607\/RSS.2019.XV.011","DOI":"10.15607\/RSS.2019.XV.011"},{"key":"29_CR14","unstructured":"Hessel, M., et al.: Rainbow: combining improvements in deep reinforcement learning. In: McIlraith, S.A., Weinberger, K.Q. (eds.) AAAI, pp. 3215\u20133222. AAAI Press (2018). http:\/\/dblp.uni-trier.de\/db\/conf\/aaai\/aaai2018.html#HesselMHSODHPAS18"},{"key":"29_CR15","unstructured":"Horgan, D., et al.: Distributed prioritized experience replay. In: International Conference on Learning Representations (2018). https:\/\/openreview.net\/forum?id=H1Dy---0Z"},{"key":"29_CR16","unstructured":"Kapturowski, S., Ostrovski, G., Dabney, W., Quan, J., Munos, R.: Recurrent experience replay in distributed reinforcement learning. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=r1lyTjAqYX"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Kempka, M., Wydmuch, M., Runc, G., Toczek, J., Ja\u015bkowski, W.: ViZDoom: a doom-based AI research platform for visual reinforcement learning. In: IEEE Conference on Computational Intelligence and Games, Santorini, Greece, pp. 341\u2013348. IEEE, September 2016. http:\/\/arxiv.org\/abs\/1605.02097. The best paper award","DOI":"10.1109\/CIG.2016.7860433"},{"key":"29_CR18","unstructured":"Kim, Y., Nam, W., Kim, H., Kim, J.H., Kim, G.: Curiosity-bottleneck: exploration by distilling task-specific novelty. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning. Machine Learning Research, 09\u201315 June 2019, vol. 97, pp. 3379\u20133388. PMLR (2019). http:\/\/proceedings.mlr.press\/v97\/kim19c.html"},{"key":"29_CR19","unstructured":"Laversanne-Finot, A., P\u00e9r\u00e9, A., Oudeyer, P.: Curiosity driven exploration of learned disentangled goal spaces. In: Proceedings of the 2nd Annual Conference on Robot Learning, CoRL 2018, Z\u00fcrich, Switzerland, 29\u201331 October 2018. Machine Learning Research, vol. 87, pp. 487\u2013504. PMLR (2018). http:\/\/proceedings.mlr.press\/v87\/laversanne-finot18a.html"},{"key":"29_CR20","unstructured":"Lee, L., Eysenbach, B., Parisotto, E., Xing, E.P., Levine, S., Salakhutdinov, R.: Efficient exploration via state marginal matching. CoRR abs\/1906.05274 (2019). http:\/\/arxiv.org\/abs\/1906.05274"},{"key":"29_CR21","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17, 39:1\u201339:40 (2015)"},{"key":"29_CR22","unstructured":"Machado, M.C., Bellemare, M.G., Bowling, M.: A laplacian framework for option discovery in reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning, ICML\u201917, vol. 70, pp. 2295\u20132304. JMLR.org (2017)"},{"key":"29_CR23","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"29_CR24","unstructured":"O\u2019Donoghue, B., Osband, I., Munos, R., Mnih, V.: The uncertainty bellman equation and exploration. In: Dy, J.G., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, 10\u201315 July 2018. Machine Learning Research, vol. 80, pp. 3836\u20133845. PMLR (2018). http:\/\/proceedings.mlr.press\/v80\/o-donoghue18a.html"},{"key":"29_CR25","unstructured":"Oh, J., Guo, Y., Singh, S., Lee, H.: Self-imitation learning. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Machine Learning Research, 10\u201315 July 2018, vol. 80, pp. 3878\u20133887. PMLR (2018). http:\/\/proceedings.mlr.press\/v80\/oh18b.html"},{"key":"29_CR26","unstructured":"Osband, I., Blundell, C., Pritzel, A., Roy, B.V.: Deep exploration via bootstrapped DQN. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS\u201916, Red Hook, NY, USA, pp. 4033\u20134041. Curran Associates Inc. (2016)"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 488\u2013489 (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"29_CR28","unstructured":"Savinov, N., et al.: Episodic curiosity through reachability. In: International Conference on Learning Representations (2019). https:\/\/openreview.net\/forum?id=SkeK3s0qKQ"},{"issue":"7839","key":"29_CR29","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., et al.: Mastering Atari, Go, chess and shogi by planning with a learned model. Nature 588(7839), 604\u2013609 (2020). https:\/\/doi.org\/10.1038\/s41586-020-03051-4","journal-title":"Nature"},{"key":"29_CR30","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. CoRR abs\/1707.06347 (2017). http:\/\/arxiv.org\/abs\/1707.06347"},{"key":"29_CR31","unstructured":"Sekar, R., Rybkin, O., Daniilidis, K., Abbeel, P., Hafner, D., Pathak, D.: Planning to explore via self-supervised world models. In: International Conference on Machine Learning (2020)"},{"key":"29_CR32","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. Nat. 550, 354\u2013359 (2017)","journal-title":"Nat."},{"key":"29_CR33","doi-asserted-by":"publisher","unstructured":"Song, Y., et al.: Mega-reward: achieving human-level play without extrinsic rewards. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 04, pp. 5826\u20135833, April 2020. https:\/\/doi.org\/10.1609\/aaai.v34i04.6040. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/6040","DOI":"10.1609\/aaai.v34i04.6040"},{"key":"29_CR34","unstructured":"Stanton, C., Clune, J.: Deep curiosity search: intra-life exploration improves performance on challenging deep reinforcement learning problems. CoRR abs\/1806.00553 (2018). http:\/\/arxiv.org\/abs\/1806.00553"},{"key":"29_CR35","unstructured":"Sukhbaatar, S., Lin, Z., Kostrikov, I., Synnaeve, G., Szlam, A., Fergus, R.: Intrinsic motivation and automatic curricula via asymmetric self-play. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, 30 April\u20133 May 2018, Conference Track Proceedings. OpenReview.net (2018). https:\/\/openreview.net\/forum?id=SkT5Yg-RZ"},{"key":"29_CR36","unstructured":"Vezhnevets, A.S., et al.: Feudal networks for hierarchical reinforcement learning. In: Proceedings of the 34th International Conference on Machine Learning, ICML\u201917, vol. 70, pp. 3540\u20133549. JMLR.org (2017)"},{"issue":"7782","key":"29_CR37","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). https:\/\/doi.org\/10.1038\/s41586-019-1724-z","journal-title":"Nature"}],"container-title":["Lecture Notes in Computer Science","AIxIA 2021 \u2013 Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-08421-8_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T21:06:55Z","timestamp":1658178415000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-08421-8_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031084201","9783031084218"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-08421-8_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 July 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AIxIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of the Italian Association for Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"aiia2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/aixia2021.disco.unimib.it\/","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":"58","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":"36","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":"62% - 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":"2","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)"}}]}}