{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:47:49Z","timestamp":1757310469617,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031539657"},{"type":"electronic","value":"9783031539664"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-53966-4_14","type":"book-chapter","created":{"date-parts":[[2024,2,14]],"date-time":"2024-02-14T18:02:29Z","timestamp":1707933749000},"page":"177-191","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Improving Reinforcement Learning Efficiency with\u00a0Auxiliary Tasks in\u00a0Non-visual Environments: A\u00a0Comparison"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7109-7813","authenticated-orcid":false,"given":"Moritz","family":"Lange","sequence":"first","affiliation":[]},{"given":"Noah","family":"Krystiniak","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1463-2706","authenticated-orcid":false,"given":"Raphael C.","family":"Engelhardt","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1343-4209","authenticated-orcid":false,"given":"Wolfgang","family":"Konen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6237-740X","authenticated-orcid":false,"given":"Laurenz","family":"Wiskott","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,2,15]]},"reference":[{"key":"14_CR1","doi-asserted-by":"publisher","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 (2015). https:\/\/doi.org\/10.1109\/IJCNN.2015.7280824","DOI":"10.1109\/IJCNN.2015.7280824"},{"key":"14_CR2","unstructured":"Andrychowicz, M., et al.: Hindsight experience replay. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"14_CR3","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv:1606.01540 [cs] (2016)"},{"issue":"3","key":"14_CR4","doi-asserted-by":"publisher","first-page":"1394","DOI":"10.1109\/LRA.2018.2800101","volume":"3","author":"T de Bruin","year":"2018","unstructured":"de Bruin, T., Kober, J., Tuyls, K., Babuska, R.: Integrating state representation learning into deep reinforcement learning. IEEE Robot. Autom. Lett. 3(3), 1394\u20131401 (2018). https:\/\/doi.org\/10.1109\/LRA.2018.2800101","journal-title":"IEEE Robot. Autom. Lett."},{"key":"14_CR5","doi-asserted-by":"publisher","unstructured":"Dulac-Arnold, G., Mankowitz, D., Hester, T.: Challenges of real-world reinforcement learning (2019). https:\/\/doi.org\/10.48550\/arXiv.1904.12901, arXiv:1904.12901 [cs, stat]","DOI":"10.48550\/arXiv.1904.12901"},{"key":"14_CR6","unstructured":"Fujimoto, S.: TD3 implementation in PyTorch (2022). https:\/\/github.com\/sfujim\/TD3"},{"key":"14_CR7","doi-asserted-by":"publisher","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods (2018). https:\/\/doi.org\/10.48550\/arXiv.1802.09477, arXiv:1802.09477 [cs, stat]","DOI":"10.48550\/arXiv.1802.09477"},{"key":"14_CR8","doi-asserted-by":"publisher","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor (2018). https:\/\/doi.org\/10.48550\/arXiv.1801.01290, arXiv:1801.01290 [cs, stat]","DOI":"10.48550\/arXiv.1801.01290"},{"key":"14_CR9","doi-asserted-by":"publisher","unstructured":"Hlynsson, H.D., Wiskott, L.: Reward prediction for representation learning and reward shaping (2021). https:\/\/doi.org\/10.48550\/arXiv.2105.03172, arXiv:2105.03172 [cs, stat]","DOI":"10.48550\/arXiv.2105.03172"},{"key":"14_CR10","doi-asserted-by":"publisher","unstructured":"van Hoof, H., Chen, N., Karl, M., van der Smagt, P., Peters, J.: Stable reinforcement learning with autoencoders for tactile and visual data. In: 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3928\u20133934 (2016). https:\/\/doi.org\/10.1109\/IROS.2016.7759578","DOI":"10.1109\/IROS.2016.7759578"},{"key":"14_CR11","doi-asserted-by":"publisher","unstructured":"Jaderberg, M., et al.: Reinforcement learning with unsupervised auxiliary tasks (2016). https:\/\/doi.org\/10.48550\/arXiv.1611.05397, arXiv:1611.05397 [cs]","DOI":"10.48550\/arXiv.1611.05397"},{"issue":"3","key":"14_CR12","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/s10514-015-9459-7","volume":"39","author":"R Jonschkowski","year":"2015","unstructured":"Jonschkowski, R., Brock, O.: Learning state representations with robotic priors. Auton. Robot. 39(3), 407\u2013428 (2015). https:\/\/doi.org\/10.1007\/s10514-015-9459-7","journal-title":"Auton. Robot."},{"issue":"8","key":"14_CR13","doi-asserted-by":"publisher","first-page":"e1000894","DOI":"10.1371\/journal.pcbi.1000894","volume":"6","author":"R Legenstein","year":"2010","unstructured":"Legenstein, R., Wilbert, N., Wiskott, L.: Reinforcement learning on slow features of high-dimensional input streams. PLoS Comput. Biol. 6(8), e1000894 (2010). https:\/\/doi.org\/10.1371\/journal.pcbi.1000894","journal-title":"PLoS Comput. Biol."},{"key":"14_CR14","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/j.neunet.2018.07.006","volume":"108","author":"T Lesort","year":"2018","unstructured":"Lesort, T., D\u00edaz-Rodr\u00edguez, N., Goudou, J.F., Filliat, D.: State representation learning for control: an overview. Neural Netw. 108, 379\u2013392 (2018). https:\/\/doi.org\/10.1016\/j.neunet.2018.07.006","journal-title":"Neural Netw."},{"key":"14_CR15","unstructured":"Lin, X., Baweja, H., Kantor, G., Held, D.: Adaptive auxiliary task weighting for reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"14_CR16","unstructured":"Locatello, F., et al.: Challenging common assumptions in the unsupervised learning of disentangled representations. arXiv:1811.12359 [cs, stat] (2019)"},{"key":"14_CR17","doi-asserted-by":"publisher","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning (2013). https:\/\/doi.org\/10.48550\/arXiv.1312.5602, arXiv:1312.5602 [cs]","DOI":"10.48550\/arXiv.1312.5602"},{"key":"14_CR18","doi-asserted-by":"publisher","unstructured":"Munk, J., Kober, J., Babuska, R.: Learning state representation for deep actor-critic control. In: 2016 IEEE 55th Conference on Decision and Control (CDC), pp. 4667\u20134673. IEEE, Las Vegas (2016). https:\/\/doi.org\/10.1109\/CDC.2016.7798980","DOI":"10.1109\/CDC.2016.7798980"},{"key":"14_CR19","unstructured":"Oh, J., Singh, S., Lee, H.: Value prediction network. In: Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)"},{"key":"14_CR20","unstructured":"Ota, K., Oiki, T., Jha, D., Mariyama, T., Nikovski, D.: Can increasing input dimensionality improve deep reinforcement learning? In: International Conference on Machine Learning, pp. 7424\u20137433. PMLR (2020)"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: Proceedings of the 34th International Conference on Machine Learning, pp. 2778\u20132787. PMLR (2017)","DOI":"10.1109\/CVPRW.2017.70"},{"key":"14_CR22","doi-asserted-by":"publisher","unstructured":"Plappert, M., et al.: Multi-goal reinforcement learning: challenging robotics environments and request for research (2018). https:\/\/doi.org\/10.48550\/arXiv.1802.09464, arXiv:1802.09464 [cs]","DOI":"10.48550\/arXiv.1802.09464"},{"key":"14_CR23","unstructured":"Raffin, A.: RL Baselines3 zoo (2020). https:\/\/github.com\/DLR-RM\/rl-baselines3-zoo"},{"issue":"268","key":"14_CR24","first-page":"1","volume":"22","author":"A Raffin","year":"2021","unstructured":"Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1\u20138 (2021)","journal-title":"J. Mach. Learn. Res."},{"key":"14_CR25","unstructured":"Shelhamer, E., Mahmoudieh, P., Argus, M., Darrell, T.: Loss is its own reward: self-supervision for reinforcement learning. arXiv:1612.07307 [cs] (2017)"},{"key":"14_CR26","unstructured":"Stooke, A., Lee, K., Abbeel, P., Laskin, M.: Decoupling representation learning from reinforcement learning. In: International Conference on Machine Learning, pp. 9870\u20139879. PMLR (2021)"},{"key":"14_CR27","doi-asserted-by":"publisher","unstructured":"Wahlstr\u00f6m, N., Sch\u00f6n, T.B., Deisenroth, M.P.: From pixels to torques: policy learning with deep dynamical Models (2015). https:\/\/doi.org\/10.48550\/arXiv.1502.02251, arXiv:1502.02251 [cs, stat]","DOI":"10.48550\/arXiv.1502.02251"},{"key":"14_CR28","unstructured":"Yarats, D., Kostrikov, I.: Soft actor-critic (SAC) implementation in PyTorch (2022). https:\/\/github.com\/denisyarats\/pytorch_sac"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-53966-4_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,14]],"date-time":"2024-02-14T18:04:37Z","timestamp":1707933877000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-53966-4_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031539657","9783031539664"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-53966-4_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"15 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning, Optimization, and Data Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grasmere","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2023.icas.cc\/","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":"In-house system and EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"119","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":"72","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":"61% - 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":"5-6","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":"1-2","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)"}}]}}