{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:57:00Z","timestamp":1773154620366,"version":"3.50.1"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030954581","type":"print"},{"value":"9783030954598","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\/978-3-030-95459-8_10","type":"book-chapter","created":{"date-parts":[[2022,2,17]],"date-time":"2022-02-17T19:02:27Z","timestamp":1645124547000},"page":"158-173","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Unsupervised Real-Time Control Through Variational Empowerment"],"prefix":"10.1007","author":[{"given":"Maximilian","family":"Karl","sequence":"first","affiliation":[]},{"given":"Philip","family":"Becker-Ehmck","sequence":"additional","affiliation":[]},{"given":"Maximilian","family":"Soelch","sequence":"additional","affiliation":[]},{"given":"Djalel","family":"Benbouzid","sequence":"additional","affiliation":[]},{"given":"Patrick","family":"van der Smagt","sequence":"additional","affiliation":[]},{"given":"Justin","family":"Bayer","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,17]]},"reference":[{"issue":"5","key":"10_CR1","doi-asserted-by":"publisher","first-page":"307","DOI":"10.2976\/1.3171566","volume":"3","author":"D Polani","year":"2009","unstructured":"Polani, D.: Information: currency of life? HFSP J. 3(5), 307\u2013316 (2009)","journal-title":"HFSP J."},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Klyubin, A.S., Polani, D., Nehaniv, C.L.: Empowerment: a universal agent-centric measure of control. In: The 2005 IEEE Congress on Evolutionary Computation, vol. 1, pp. 128\u2013135. IEEE (2005a)","DOI":"10.1109\/CEC.2005.1554676"},{"key":"10_CR3","unstructured":"Mohamed, S., Rezende, D.J.: Variational information maximisation for intrinsically motivated reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 2125\u20132133 (2015)"},{"key":"10_CR4","unstructured":"Karl, M., Bayer, J., van der Smagt, P.: Efficient empowerment. arXiv:1509.08455, September 2015"},{"key":"10_CR5","unstructured":"Karl, M., Soelch, M., Bayer, J., van der Smagt, P.: Deep variational Bayes filters: unsupervised learning of state space models from raw data. In: Proceedings of the International Conference on Learning Representations (ICLR) (2017)"},{"key":"10_CR6","unstructured":"Stengel, R.F.: Optimal Control and Estimation. Courier Corporation (2012)"},{"key":"10_CR7","unstructured":"Barber, D., Agakov, F.V.: The IM algorithm: a variational approach to information maximization. In: Advances in Neural Information Processing Systems, vol. 16, pp. 201\u2013208 (2003)"},{"key":"10_CR8","unstructured":"Rezende, D.J., Mohamed, S.: Variational inference with normalizing flows. In: Proceedings of the 32nd International Conference on Machine Learning, ICML 2015, pp. 1530\u20131538 (2015)"},{"key":"10_CR9","unstructured":"Burda, Y., Grosse, R., Salakhutdinov, R.: Importance weighted autoencoders. arXiv preprint arXiv:1509.00519 (2015)"},{"key":"10_CR10","unstructured":"Kingma, D.P., Salimans, T., J\u00f3zefowicz, R., Chen, X., Sutskever, I., Welling, M.: Improving variational autoencoders with inverse autoregressive flow. In: Advances in Neural Information Processing Systems, vol. 29, pp. 4736\u20134744 (2016)"},{"key":"10_CR11","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: Proceedings of the 2nd International Conference on Learning Representations (ICLR) (2014)"},{"key":"10_CR12","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: Proceedings of the 31th International Conference on Machine Learning, ICML 2014, pp. 1278\u20131286 (2014)"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., McClelland, J.L. (eds.) Parallel Distributed Processing, vol. 1, pp. 318\u2013362. MIT Press (1986)","DOI":"10.21236\/ADA164453"},{"key":"10_CR14","unstructured":"Rawlik, K., Toussaint, M., Vijayakumar, S.: Approximate inference and stochastic optimal control. arXiv preprint arXiv:1009.3958 (2010)"},{"key":"10_CR15","series-title":"Emergence, Complexity and Computation","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1007\/978-3-642-53734-9_4","volume-title":"Guided Self-Organization: Inception","author":"C Salge","year":"2014","unstructured":"Salge, C., Glackin, C., Polani, D.: Empowerment\u2013an introduction. In: Prokopenko, M. (ed.) Guided Self-Organization: Inception. ECC, vol. 9, pp. 67\u2013114. Springer, Heidelberg (2014). https:\/\/doi.org\/10.1007\/978-3-642-53734-9_4"},{"issue":"12","key":"10_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0004018","volume":"3","author":"AS Klyubin","year":"2008","unstructured":"Klyubin, A.S., Polani, D., Nehaniv, C.L.: Keep your options open: an information-based driving principle for sensorimotor systems. PLoS ONE 3(12), 1\u201314 (2008). https:\/\/doi.org\/10.1371\/journal.pone.0004018","journal-title":"PLoS ONE"},{"issue":"4","key":"10_CR17","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1109\/TIT.1972.1054855","volume":"18","author":"R Blahut","year":"1972","unstructured":"Blahut, R.: Computation of channel capacity and rate-distortion functions. IEEE Trans. Inf. Theory 18(4), 460\u2013473 (1972)","journal-title":"IEEE Trans. Inf. Theory"},{"issue":"1","key":"10_CR18","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1177\/1059712310392389","volume":"19","author":"T Jung","year":"2011","unstructured":"Jung, T., Polani, D., Stone, P.: Empowerment for continuous agent-environment systems. Adapt. Behav. Anim. Animats Softw. Agents Robots Adapt. Syst. 19(1), 16\u201339 (2011). https:\/\/doi.org\/10.1177\/1059712310392389. ISSN: 1059-7123","journal-title":"Adapt. Behav. Anim. Animats Softw. Agents Robots Adapt. Syst."},{"issue":"02n03","key":"10_CR19","doi-asserted-by":"publisher","first-page":"1250079","DOI":"10.1142\/S0219525912500798","volume":"16","author":"C Salge","year":"2013","unstructured":"Salge, C., Glackin, C., Polani, D.: Approximation of empowerment in the continuous domain. Adv. Complex Syst. 16(02n03), 1250079 (2013). https:\/\/doi.org\/10.1142\/S0219525912500798. ISSN: 0219-5259, 1793-6802","journal-title":"Adv. Complex Syst."},{"key":"10_CR20","unstructured":"Gregor, K., Rezende, D.J., Wierstra, D.: Variational intrinsic control. arXiv preprint arXiv:1611.07507 (2016)"},{"issue":"1\u20132","key":"10_CR21","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/S0004-3702(99)00052-1","volume":"112","author":"RS Sutton","year":"1999","unstructured":"Sutton, R.S., Precup, D., Singh, S.: Between MDPs and semi-MDPs: a framework for temporal abstraction in reinforcement learning. Artif. Intell. 112(1\u20132), 181\u2013211 (1999)","journal-title":"Artif. Intell."},{"key":"10_CR22","doi-asserted-by":"crossref","unstructured":"Singh, S.P., Barto, A.G., Chentanez, N.: Intrinsically motivated reinforcement learning. In: NIPS, pp. 1281\u20131288 (2004)","DOI":"10.21236\/ADA440280"},{"key":"10_CR23","unstructured":"Oudeyer, P.-Y., Kaplan, F.: How can we define intrinsic motivation? In: Proceedings of the 8th International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems. Lund University Cognitive Studies, Lund: LUCS, Brighton (2008)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Schmidhuber, J.: Curious model-building control systems. In: IEEE International Joint Conference on Neural Networks, pp. 1458\u20131463. IEEE (1991)","DOI":"10.1109\/IJCNN.1991.170605"},{"issue":"3","key":"10_CR25","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1109\/TAMD.2010.2056368","volume":"2","author":"J Schmidhuber","year":"2010","unstructured":"Schmidhuber, J.: Formal theory of creativity, fun, and intrinsic motivation (1990\u20132010). IEEE Trans. Auton. Ment. Dev. 2(3), 230\u2013247 (2010)","journal-title":"IEEE Trans. Auton. Ment. Dev."},{"key":"10_CR26","unstructured":"Bellemare, M.G., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. In: Advances in Neural Information Processing Systems, vol. 29, pp. 1471\u20131479 (2016)"},{"key":"10_CR27","unstructured":"Itti, L., Baldi, P.F.: Bayesian surprise attracts human attention. In: Advances in Neural Information Processing Systems, pp. 547\u2013554 (2006)"},{"key":"10_CR28","unstructured":"Achiam, J., Sastry, S.: Surprise-based intrinsic motivation for deep reinforcement learning. arXiv preprint arXiv:1703.01732 (2017)"},{"key":"10_CR29","unstructured":"Houthooft, R., Chen, X., Duan, Y., Schulman, J., De Turck, F., Abbeel, P.: VIME: variational information maximizing exploration. In: Advances in Neural Information Processing Systems, pp. 1109\u20131117 (2016)"},{"key":"10_CR30","doi-asserted-by":"publisher","first-page":"313","DOI":"10.3389\/fpsyg.2013.00313","volume":"4","author":"J Schmidhuber","year":"2013","unstructured":"Schmidhuber, J.: PowerPlay: training an increasingly general problem solver by continually searching for the simplest still unsolvable problem. Front. Psychol. 4, 313 (2013)","journal-title":"Front. Psychol."},{"key":"10_CR31","unstructured":"Sukhbaatar, S., Kostrikov, I., Szlam, A., Fergus, R.: Intrinsic motivation and automatic curricula via asymmetric self-play. arXiv preprint arXiv:1703.05407 (2017)"},{"issue":"16","key":"10_CR32","doi-asserted-by":"publisher","first-page":"168702","DOI":"10.1103\/PhysRevLett.110.168702","volume":"110","author":"AD Wissner-Gross","year":"2013","unstructured":"Wissner-Gross, A.D., Freer, C.E.: Causal entropic forces. Phys. Rev. Lett. 110(16), 168702 (2013)","journal-title":"Phys. Rev. Lett."},{"key":"10_CR33","unstructured":"Coumans, E., Bai, Y.: PyBullet, a Python module for physics simulation for games, robotics and machine learning. GitHub repository (2016)"},{"key":"10_CR34","doi-asserted-by":"publisher","unstructured":"Klyubin, A.S., Polani, D., Nehaniv, C.L.: All else being equal be empowered. In: Capcarr\u00e8re, M.S., Freitas, A.A., Bentley, P.J., Johnson, C.G., Timmis, J. (eds.) ECAL 2005. LNCS (LNAI), vol. 3630, pp. 744\u2013753. Springer, Heidelberg (2005b). https:\/\/doi.org\/10.1007\/11553090_75","DOI":"10.1007\/11553090_75"},{"key":"10_CR35","unstructured":"Brockman, G., et al.: OpenAI gym (2016)"}],"container-title":["Springer Proceedings in Advanced Robotics","Robotics Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-95459-8_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T20:57:37Z","timestamp":1726693057000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-95459-8_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030954581","9783030954598"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-95459-8_10","relation":{},"ISSN":["2511-1256","2511-1264"],"issn-type":[{"value":"2511-1256","type":"print"},{"value":"2511-1264","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 February 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISRR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The International Symposium of Robotics Research","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 October 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 October 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isrr2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/h2t-projects.webarchiv.kit.edu\/Projects\/ISRR2019\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}