{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,14]],"date-time":"2025-12-14T08:29:09Z","timestamp":1765700949349,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319999777"},{"type":"electronic","value":"9783319999784"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Bounded rationality investigates utility-optimizing decision-makers with limited information-processing power. In particular, information theoretic bounded rationality models formalize resource constraints abstractly in terms of relative Shannon information, namely the Kullback-Leibler Divergence between the agents\u2019 prior and posterior policy. Between prior and posterior lies an anytime deliberation process that can be instantiated by sample-based evaluations of the utility function through Markov Chain Monte Carlo (MCMC) optimization. The most simple model assumes a fixed prior and can relate abstract information-theoretic processing costs to the number of sample evaluations. However, more advanced models would also address the question of learning, that is how the prior is adapted over time such that generated prior proposals become more efficient. In this work we investigate generative neural networks as priors that are optimized concurrently with anytime sample-based decision-making processes such as MCMC. We evaluate this approach on toy examples.<\/jats:p>","DOI":"10.1007\/978-3-319-99978-4_17","type":"book-chapter","created":{"date-parts":[[2018,8,30]],"date-time":"2018-08-30T02:07:12Z","timestamp":1535594832000},"page":"213-225","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Bounded Rational Decision-Making with Adaptive Neural Network Priors"],"prefix":"10.1007","author":[{"given":"Heinke","family":"Hihn","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sebastian","family":"Gottwald","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel A.","family":"Braun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,8,30]]},"reference":[{"key":"17_CR1","unstructured":"Andrieu, C., De Freitas, N., Doucet, A.: Reversible jump MCMC simulated annealing for neural networks. In: Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence, pp. 11\u201318. Morgan Kaufmann Publishers Inc. (2000)"},{"key":"17_CR2","unstructured":"Chollet, F., et al.: Keras (2015). https:\/\/keras.io"},{"issue":"4","key":"17_CR3","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1111\/cogs.12101","volume":"38","author":"E Vul","year":"2014","unstructured":"Vul, E., Goodman, N., Griffiths, T.L., Tenenbaum, J.B.: One and done? Optimal decisions from very few samples. Cogn. Sci. 38(4), 599\u2013637 (2014)","journal-title":"Cogn. Sci."},{"issue":"4","key":"17_CR4","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1162\/089976600300015664","volume":"12","author":"J Freitas","year":"2000","unstructured":"Freitas, J., Niranjan, M., Gee, A.H., Doucet, A.: Sequential Monte Carlo methods to train neural network models. Neural Comput. 12(4), 955\u2013993 (2000)","journal-title":"Neural Comput."},{"key":"17_CR5","doi-asserted-by":"publisher","first-page":"27","DOI":"10.3389\/frobt.2015.00027","volume":"2","author":"T Genewein","year":"2015","unstructured":"Genewein, T., Leibfried, F., Grau-Moya, J., Braun, D.A.: Bounded rationality, abstraction, and hierarchical decision-making: an information-theoretic optimality principle. Front. Robot. AI 2, 27 (2015)","journal-title":"Front. Robot. AI"},{"key":"17_CR6","unstructured":"Ghosh, D., Singh, A., Rajeswaran, A., Kumar, V., Levine, S.: Divide-and-conquer reinforcement learning. arXiv preprint arXiv:1711.09874 (2017)"},{"key":"17_CR7","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1007\/978-3-319-46227-1_30","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"J Grau-Moya","year":"2016","unstructured":"Grau-Moya, J., Leibfried, F., Genewein, T., Braun, D.A.: Planning with information-processing constraints and model uncertainty in Markov decision processes. In: Frasconi, P., Landwehr, N., Manco, G., Vreeken, J. (eds.) ECML PKDD 2016. LNCS (LNAI), vol. 9852, pp. 475\u2013491. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46227-1_30"},{"key":"17_CR8","unstructured":"Gu, S., Ghahramani, Z., Turner, R.E.: Neural adaptive sequential Monte Carlo. In: Advances in Neural Information Processing Systems, pp. 2629\u20132637 (2015)"},{"issue":"10","key":"17_CR9","doi-asserted-by":"publisher","first-page":"2201","DOI":"10.1162\/089976601750541778","volume":"13","author":"M Haruno","year":"2001","unstructured":"Haruno, M., Wolpert, D.M., Kawato, M.: Mosaic model for sensorimotor learning and control. Neural Comput. 13(10), 2201\u20132220 (2001)","journal-title":"Neural Comput."},{"key":"17_CR10","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"issue":"8","key":"17_CR11","doi-asserted-by":"publisher","first-page":"1686","DOI":"10.1162\/NECO_a_00758","volume":"27","author":"F Leibfried","year":"2015","unstructured":"Leibfried, F., Braun, D.A.: A reward-maximizing spiking neuron as a bounded rational decision maker. Neural Comput. 27(8), 1686\u20131720 (2015)","journal-title":"Neural Comput."},{"key":"17_CR12","unstructured":"Leibfried, F., Grau-Moya, J., Ammar, H.B.: An information-theoretic optimality principle for deep reinforcement learning. arXiv preprint arXiv:1708.01867 (2017)"},{"key":"17_CR13","unstructured":"Levy, D., Hoffman, M.D., Sohl-Dickstein, J.: Generalizing Hamiltonian Monte Carlo with neural networks. In: International Conference on Learning Representations (2018)"},{"issue":"2","key":"17_CR14","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1111\/tops.12086","volume":"6","author":"RL Lewis","year":"2014","unstructured":"Lewis, R.L., Howes, A., Singh, S.: Computational rationality: linking mechanism and behavior through bounded utility maximization. Top. Cogn. Sci. 6(2), 279\u2013311 (2014)","journal-title":"Top. Cogn. Sci."},{"key":"17_CR15","series-title":"NATO ASI Series (Series D: Behavioural and Social Sciences)","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/978-94-011-5014-9_7","volume-title":"Learning in Graphical Models","author":"DJC MacKay","year":"1998","unstructured":"MacKay, D.J.C.: Introduction to Monte Carlo methods. In: Jordan, M.I. (ed.) Learning in Graphical Models. ASID, vol. 89, pp. 175\u2013204. Springer, Dordrecht (1998). https:\/\/doi.org\/10.1007\/978-94-011-5014-9_7"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Ortega, P.A., Braun, D.A.: Thermodynamics as a theory of decision-making with information-processing costs. Proc. R. Soc. Lond. A: Math. Phys. Eng. Sci. 469(2153) (2013)","DOI":"10.1098\/rspa.2012.0683"},{"key":"17_CR17","unstructured":"Ortega, P.A., Braun, D.A., Dyer, J., Kim, K.E., Tishby, N.: Information-theoretic bounded rationality. arXiv preprint arXiv:1512.06789 (2015)"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Peng, Z., Genewein, T., Leibfried, F., Braun, D.A.: An information-theoretic on-line update principle for perception-action coupling. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 789\u2013796. IEEE (2017)","DOI":"10.1109\/IROS.2017.8202240"},{"issue":"7587","key":"17_CR19","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"17_CR20","series-title":"Springer Series in Cognitive and Neural Systems","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1007\/978-1-4419-1452-1_19","volume-title":"Perception-Action Cycle: Models, Architectures, and Hardware","author":"N Tishby","year":"2011","unstructured":"Tishby, N., Polani, D.: Information theory of decisions and actions. In: Cutsuridis, V., Hussain, A., Taylor, J. (eds.) Perception-Action Cycle: Models, Architectures, and Hardware. SSCNS, pp. 601\u2013636. Springer, New York (2011). https:\/\/doi.org\/10.1007\/978-1-4419-1452-1_19"},{"issue":"28","key":"17_CR21","doi-asserted-by":"publisher","first-page":"11478","DOI":"10.1073\/pnas.0710743106","volume":"106","author":"E Todorov","year":"2009","unstructured":"Todorov, E.: Efficient computation of optimal actions. Proc. Natl. Acad. Sci. 106(28), 11478\u201311483 (2009)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"17_CR22","volume-title":"Theory of Games and Economic Behavior","author":"J Von Neumann","year":"2007","unstructured":"Von Neumann, J., Morgenstern, O.: Theory of Games and Economic Behavior, Commemorative edn. Princeton University Press, Princeton (2007)","edition":"Commemorative"},{"key":"17_CR23","series-title":"Understanding Complex Systems","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1007\/3-540-32834-3_12","volume-title":"Complex Engineered Systems: Science Meets Technology","author":"DH Wolpert","year":"2006","unstructured":"Wolpert, D.H.: Information theory - the bridge connecting bounded rational game theory and statistical physics. In: Braha, D., Minai, A., Bar-Yam, Y. (eds.) Complex Engineered Systems: Science Meets Technology. UCS, pp. 262\u2013290. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/3-540-32834-3_12"},{"issue":"8","key":"17_CR24","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.1109\/TNNLS.2012.2200299","volume":"23","author":"SE Yuksel","year":"2012","unstructured":"Yuksel, S.E., Wilson, J.N., Gader, P.D.: Twenty years of mixture of experts. IEEE Trans. Neural Netw. Learn. Syst. 23(8), 1177\u20131193 (2012)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks in Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-99978-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,11]],"date-time":"2023-07-11T14:04:39Z","timestamp":1689084279000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-99978-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319999777","9783319999784"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-99978-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"30 August 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ANNPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IAPR Workshop on Artificial Neural Networks in Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Siena","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"annpr2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/annpr2018.diism.unisi.it\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}