Formal Theory of Creativity, Fun, and Intrinsic Motivation (1990–2010)
The DOI matches its Crossref record; 125 of the 126 references it cites were found in a registry or an index.
Abstract
The simple, but general formal theory of fun and intrinsic motivation and creativity (1990-2010) is based on the concept of maximizing intrinsic reward for the active creation or discovery of novel, surprising patterns allowing for improved prediction or data compression. It generalizes the traditional field of active learning, and is related to old, but less formal ideas in aesthetics theory and developmental psychology. It has been argued that the theory explains many essential aspects of intelligence including autonomous development, science, art, music, and humor. This overview first describes theoretically optimal (but not necessarily practical) ways of implementing the basic computational principles on exploratory, intrinsically motivated agents or robots, encouraging them to provoke event sequences exhibiting previously unknown, but learnable algorithmic regularities. Emphasis is put on the importance of limited computational resources for online prediction and compression. Discrete and continuous time formulations are given. Previous practical, but nonoptimal implementations (1991, 1995, and 1997-2002) are reviewed, as well as several recent variants by others (2005-2010). A simplified typology addresses current confusion concerning the precise nature of intrinsic motivation.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This underwrites Bayesian experimental design [134] and active learning in statistics [135], intrinsic motivation and artificial curiosity in machine learning and robotics [136, 137, 138, 139, 140].”
From The free energy principle made simpler but not too simple (2023) · cites this paper as [137]
In the citing paper
“This suggests that risk-averse policies minimise expected complexity or computational cost [137].”
From The free energy principle made simpler but not too simple (2023) · cites this paper as [137]
In the citing paper
“Ideally, the learner learns to choose actions that will lead to the largest improvements in its prediction or data compression performance (Schmidhuber, 2010).”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Schmidhuber, 2010
In the citing paper
“In Schmidhuber (2010), this is done in the framework of reinforcement learning, and incorporates a mechanisms for the system to measure its own rate of learning.”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Schmidhuber, 2010
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 7×
“Another potential drawback is the nature of the particular RNN-based RL method.”
BackgroundInfluentialSelf-citationA Mathematical Theory of Communication
Shannon, C. E. (1948) · Bell System Technical Journal · doi:10.1002/j.1538-7305.1948.tb01338.x · Cited by 88,486
Holland, J. H. (1992) · The MIT Press eBooks · doi:10.7551/mitpress/1090.001.0001 · Cited by 47,002 · cited 1×
“iii) An evolutionary algorithm [22], [29], [59],”
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225 · cited 7×
“Some Q-learning accelerators simply update pairs of actions and states with currently quickly changing Q-values more frequently than others (that is, Q-values with high first derivatives are favored).”
BackgroundMethodInfluentialReinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
Neural networks for pattern recognition
(1994) · Choice Reviews Online · doi:10.5860/choice.31-5500 · Cited by 18,538
Advances in neural information processing systems 7
(1996) · Computers & Mathematics with Applications · doi:10.1016/s0898-1221(96)90463-0 · Cited by 14,281
Neural Networks for Pattern Recognition
Bishop, C. M. (1995) · doi:10.1093/oso/9780198538493.001.0001 · Cited by 12,287
Watkins, C. J. C. H., & Dayan, P. (1992) · Machine Learning · doi:10.1007/bf00992698 · Cited by 9,083
Reinforcement Learning: A Survey
Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.301 · Cited by 8,972 · cited 4×
“, some typically suboptimal RL method [35].”
BackgroundMethodInfluential
Research works printed but not linked: 24
- kullback, 1959, Statistics and Information Theory
- hutter, 2004, Universal Artificial Intelligence Sequential Decisions Based on Algorithmic Probability
- holland, 1975, Adaptation in Natural and Artificial Systems
- schmidhuber, 2010, How to Learn Programs with Artificial Recurrent Neural Networks
- harlow, 1950, novelty and curiosity as determinants of exploratory behavior, J Exp Psychol, 41, 68
- berlyne, 1950, novelty and curiosity as determinants of exploratory behavior, Brit J Psychol, 41, 68
- 10.1007/bf00993591 · doi:10.1007/bf00993591 · Paper page
- levin, 1973, universal sequential search problems, Problems Inform Trans, 9, 265
- schmidhuber, 1991, Advances in Neural Information Processing Systems 3, nips 3, 500
- schmidhuber, 1997, Femmes Fractales
- schmidhuber, 2002, Advances in Evolutionary Computing, 579
- ring, 1994, Continual Learning in Reinforcement Environments
- schmidhuber, 1990, Dynamische neuronale Netze und das fundamentale raumzeitliche Lernproblem
- schmidhuber, 1991, Adaptive Curiosity and Adaptive Confidence
- schmidhuber, 2009, Compression Progress The Algorithmic Principle Behind Curiosity and Creativity (With Applications of the Theory of Humor) 40 min Video of Invited Talk at Singularity Summit 2009
- schmidhuber, 2009, Multiple Ways to Design Research Research Cases that Reshape the Design Discipline, 98
- singh, 2005, Advances in neural information processing systems, 17
- schwefel, 1974, Numerische Optimierung von Computer-Modellen
- schmidhuber, 2007, alle berechenbaren universen (all computable universes), Spektrum der Wissenschaft, 75
- storck, 1995, reinforcement driven information acquisition in non-deterministic environments, Proc Int Conf Artif Neural Netw, 2, 159
- brafman, 2002, R-MAX—A general polynomial time algorithm for near-optimal reinforcement learning, J Mach Learn Res, 3, 213
- frank, 2002, sthetische Information Estetika informacio Eine Einfhrung in die Kybernetische sthetik
- franke, 1979, Kybernetische sthetik Phnomen Kunst
- schmidhuber, 2006, Artificial General Intelligence, 175
Cited by
Items 701–800 of 886
Duan, Y. (2017) · eScholarship (California Digital Library) · Cited by 1
New tab page recommendations cause a strong suppression of exploratory web browsing behaviorsPreprint
Bharadhwaj, H., & Srivastava, N. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.06525 · Cited by 1
“This paper makes the case that, by showing people the sites they visit most frequently over and over again in new tab displays, current practice in browser and OS UI design traps people into a solipsistic feedback loop, reinforcing their strongest preferences to the detriment of weaker ones that potentially offer more…”
BackgroundHigh-Dimensional Control Using Generalized Auxiliary TasksPreprint
Flet-Berliac, Y., & Preux, P. (2019) · Cited by 1
Preschoolers search longer when there is more information to be gainedPreprint
Schulz, E., Pelz, M. C., Alison Gopnik, C., & Ruggeri, A. (2019) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/5wegk · Cited by 1
“Formally, the IG for finding the 41 animal in the known animal condition was − log(1) = 0, whereas the IG in the unknown animal condition 42 was − log(1/8) = 3.”
BackgroundClements, M. (2020) · University of Hertfordshire Research Archive (University of Hertfordshire) · doi:10.18745/th.22616 · Cited by 1
“Computational approaches to intrinsic motivation have given artificial agents the ability to exhibit explorative curiosity (Schmidhuber, 2010), an important component in intelligent behaviour.”
BackgroundAn open-ended learning architecture to face the REAL 2020 simulated robot competition.Preprint
Cartoni, E., Montella, D., Triesch, J., & Baldassarre, G. (2020) · arXiv (Cornell University) · Cited by 2
Measuring and predicting variation in the interestingness of physical structuresPreprint
Holdaway, C., Bear, D. M., Radwan, S. F., Frank, M. C., Yamins, D. L. K., & Fan, J. E. (2021) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/hg7fv · Cited by 3
“Other forms of artificial curiosity (AC) have been proposed, in various domains, to account for the emergence of more complex behaviors and to drive learning about the world (Schmidhuber, 1991, 2010; Aubret, Matignon, & Hassas, 2019).”
BackgroundThe Learning and Persistence of Aesthetic Values
Aleem, H. (2021) · DigitalGeorgetown (Georgetown University Library) · Cited by 1
Learning state-action features for general game playing
Soemers, D. J. N. J. (2023) · Research Publications (Maastricht University) · doi:10.26481/dis.20230425ds · Cited by 4
Analogical Proportions and Creativity: A Preliminary StudyPreprint
Afantenos, S., Prade, H. M., & Bernardes, L. C. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2310.13500 · Cited by 1
“Creativity has raised interest for a long time in computer sciences and in AI (Boden 2004; Schmidhuber 2010; Colton 2008) with applications in many areas.”
Diversity Progress for Goal Selection in Discriminability-Motivated RLPreprint
Lintunen, E. M., Ady, N. M., & Guckelsberger, C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.01521 · Cited by 2
“Learning Progress (LP) (e.g., Oudeyer et al., 2007; Schmidhuber, 2010) is designed “to select goals that are of learning-optimal difficulty with respect to [the agent’s] current capabilities” (Lintunen et al., 2024, p. 39).”
BackgroundCuriosity-Driven LLM-as-a-judge for Personalized Creative JudgmentPreprint
Kumar, V. B., Goyal, D. P., Eppa, A., & Bhandari, N. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2510.05135 · Cited by 1
AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification
Cho, G., Lee, J., Im, J., Lee, S., Lee, J., & Kim, S. (2025) · International Conference on Learning Representations · doi:10.48550/arxiv.2506.05980 · Cited by 1
“Efficient exploration remains a major challenge in reinforcement learning (RL), particularly in environments with sparse or delayed rewards [42, 44, 50, 27].”
Ismail, H. (2014) · UNSWorks (University of New South Wales, Sydney, Australia) · doi:10.26190/unsworks/17146 · Cited by 1
RIZE: Adaptive Regularization for Imitation Learning
Karimi, A., & Ebadzadeh, M. (2025) · Trans. Mach. Learn. Res. · doi:10.48550/arxiv.2502.20089 · Cited by 1
“…al., 2016), learning from expert trajectories (Schaal, 1996; Ng & Russell, 2000; Osa et al., 2018), human preference-based reward modeling (Christiano et al., 2017; Lee et al., 2021; Hejna & Sadigh, 2023), and intrinsically motivated RL (Oudeyer et al., 2007; Schmidhuber, 2010; Colas et al., 2022).”
Online allocation and homogeneous partitioning for piecewise constant mean-approximationPreprint
Maillard, O.-A., & Carpentier, A. (2012) · HAL · Cited by 1
Goals, Play, and Cognitive Pragmatism: A study of flexible human minds
Chu, J. (2023) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 1
Horibe, K., & Suzuki, K. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.06771 · Cited by 1
“Existing approaches typically frame behavior as the optimization of a specific objective function, such as free energy [29] 2 , empowerment [86], novelty or curiosity driven search[87, 88, 89, 90, 91, 92, 93, 94].”
Multiple Token Divergence: Measuring and Steering In-Context Computation DensityPreprint
Herrmann, V., Alcaide, E., Wand, M., & Schmidhuber, J. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.22944 · Cited by 1
“It is well-established that the next-token prediction loss offers little insight (Schmidhuber, 2010; Burda et al., 2018), as any particular reduction in loss can, in principle, be arbitrarily difficult to achieve (Bennett, 1988).”
Self-citationPappalardo, O. (2026) · International Conference on Learning Representations · doi:10.48550/arxiv.2601.19810 · Cited by 1
“…objectives that aid representation learning (Jaderberg et al., 2016; Oord et al., 2018; Zhang et al., 2020a; Stooke et al., 2021; Schwarzer et al., 2021), and training agents with intrinsic rewards (Chentanez et al., 2004; Oudeyer et al., 2007; Schmidhuber, 2010) that lead to useful behaviors.”
Artificial Agency Program: Curiosity, compression, and communication in agentsPreprint
Csáky, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.24100 · Cited by 1
“We adopt a learning-progress view of curiosity: intrinsically valuable patterns are neither random nor trivial, but those for which the agent can currently improve compression or prediction (Schmidhuber, 2010; Oudeyer et al., 2007).”
InfluentialMohamed, F., Ji, C., Eysenbach, B., & Berseth, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.02008 · Cited by 5
“Prior work on exploration (Schmidhuber, 2010; sch, 1991; Sorg et al., 2012; Brafman & Tennenholtz, 2002; Kearns & Singh, 2002) in reinforcement learning has proposed a variety of task-agnostic methods for encouraging agents to acquire diverse behaviors without relying on external rewards(also konwn…”
Hervouet, F. (2014) · theses.fr (ABES) · doi:10.70675/5b4af982z9287z44c7z9bf7z48fb464a18a0 · Cited by 1
“Nous étendons plusieurs aspects traités dans des typologies déjà proposées par le passé [Oudeyer et Kaplan, 2007; Schmidhuber, 2010; Baldassarre et Mirolli, 2013].”
BackgroundLearning sensori-motor mappings using little knowledge : application to manipulation robotics
Bourdonnaye, F. D. L. (2018) · theses.fr (ABES) · doi:10.70675/c1fd9025zeba7z4f16zb3c2z3de4fb2a60fb · Cited by 1
Ten, A. (2022) · theses.fr (ABES) · doi:10.70675/8b809eb0z5f7az4f7azb976zd94d7015a14d · Cited by 1
Learning increasingly complex skills through deep reinforcement learning using intrinsic motivation
Aubret, A. (2021) · theses.fr (ABES) · doi:10.70675/6f863351zdd37z4da4z9fa2z5ceed27ddd07 · Cited by 1
Sample-efficient deep reinforcement learning for control, exploration and safety
Flet-Berliac, Y. (2021) · theses.fr (ABES) · doi:10.70675/141a23faz45c0z40eez8d28z3b73282b4ff2 · Cited by 1
Signed Compression Progress on a Sealed Audit is Goodhart-ResistantPreprint
Mittal, A., & Gupta, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.11417 · Cited by 1
“Intrinsic motivation based on prediction or compression progress appears in Schmidhuber’s work on artificial curiosity and the later compression-progress theory of interestingness [8, 9, 10].”
COrigami: An AI Pipeline for Co-Designing Flat-Foldable Visually Recognisable OrigamiPreprint
Zahavy, T., Hou, S., Tumiel, T., Doran, J. E., Faccio, F., Feng, X., Havrilla, A., Khytryi, I., Li, C., Schut, L., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.26299 · Cited by 1
Emergence of Goal‐Directed Behaviors via Active Inference With Self‐Prior
Kim, D., Kanazawa, H., Yoshida, N., & Kuniyoshi, Y. (2026) · Developmental Science · doi:10.1111/desc.70286
“This separation ensures proper variational decomposition at each time step (implementation details in Appendix A.2.2 ).”
InfluentialHeuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty
Antoniades, A., Nathani, D., Saha, R., Amayuelas, A., Bercovich, I., Weng, Z., Baskaran, V., Bhatia, K., & Wang, W. Y. (2026) · arXiv · doi:10.48550/arxiv.2606.25198
Interestingness as an Inductive Heuristic for Future Compression Progress
Herrmann, V., & Schmidhuber, J. (2026) · arXiv · doi:10.48550/arxiv.2605.14831
“This is the “Noisy TV” problem (Schmidhuber, 2010): a subject using pure prediction error as a reward will get stuck observing a source of pure noise (like a static TV) because it is always unpredictable, yet provides zero learnable structure.”
Self-citationOn the generation of representations for reinforcement learning
Sun, Y. (2012) · reroDoc Digital Library
A Curious Vision System for Autonomous and Cumulative Object Learning
Chandrashekhariah, P., Spina, G., & Triesch, J. (2014) · Communications in computer and information science · doi:10.1007/978-3-662-44911-0_13
Universal Memory Architectures for Autonomous MachinesPreprint
Guralnik, D. P., & Koditschek, D. E. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1502.06132
Curiosity-driven learning with Context Tree Weighting
Peng, Z., & Braun, D. A. (2014) · IEEE International Conference on Development and Learning (ICDL) · doi:10.1109/devlrn.2014.6983008
AC 2011-1315: FACTORS THAT INFLUENCE THE CREATIVITY OF ENGINEERING STUDENTS
Genco, N., Hölttä‐Otto, K., & Seepersad, C. C. (2011)
of Happiness for Reinforcement Learning Agents
Daswani, M., & Leike, J. (2015)
КРЕАТИВНОСТЬ СТАРШЕКЛАССНИКОВ КАК ПРЕДИКТОР ПСИХОЛОГИЧЕСКОГО БЛАГОПОЛУЧИЯ В ШКОЛЕ
Анатольевич, В. С., & Евгеньевна, В. Ю. (2015) · Electronic archive USPU
Model and Simulate Emergent Cognition
Georgeon, O. L., & Ritter, F. E. (2011)
Learning manipulation affordances via intrinsically motivated exploration
Border, B. J. (2017) · Figshare · doi:10.4225/03/58b77bd38a928
Modeling curiosity for intelligent agents
Wu, Q. (2014) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/62194
Learning Time-Sensitive Strategies in Space FortressPreprint
Agarwal, A., Hope, R. M., & Sycara, K. P. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.06824
“Schmidhuber [25] formalized the concept of intrinsic motivation as the improvements made to a predictive model by a learning algorithm.”
BackgroundRegion Growing Curriculum Generation for Reinforcement LearningPreprint
Molchanov, A., Hausman, K., Birchfield, S. T., & Sukhatme, G. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1807.01425 · Cited by 2
Learning Good Representation via Continuous AttentionPreprint
Zhao, L., & Xu, W. H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1903.12344
“Intrinsic rewards such as prediction gain [3], learning progress [19], compression progress [22], variational information maximization [8, 26], have been employed to augment the environment’s reward signal for encouraging to discover novel behavior patterns.”
Binary Space Partitioning as Intrinsic RewardPreprint
Skaba, W. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.03611
“[2], [3].”
Learning Representations Using Reinforcement Learning
Bose, S. (2019)
Bose, S., & Huber, M. (2019) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2019.8913930
“to reduce model uncertainty, or using model predictability as an intrinsic reward to learn models for better planning [5], [6].”
MethodLearn to navigate through deep neural networks
Wu, K. (2020) · DR-NTU (Nanyang Technological University) · doi:10.32657/10356/139680
Scene Change Task: Take me to Paris.
Brugman, S., & Larson, M. (2019) · MediaEval
Machine Learning: Tools for End‐to‐End Cognition
Mwanje, S. S., Kajo, M., & Schultz, B. (2020) · Wiley eBooks · doi:10.1002/9781119586449.ch6
Experimental Mathematics: Overview and Pedagogical Implications
Danesi, M. (2020) · Mathematics in mind · doi:10.1007/978-3-030-59177-9_8
Improving Structure of the SLMHM on the Base of the PDCA CyclePreprint
Gakh, D. B. (2021) · Preprints.org · doi:10.20944/preprints202104.0490.v1
“For AI it can relate to some type of feedback (one example was presented by Schmidhuber (2010)).”
BackgroundBjare, M. R., & Meredith, D. (2020) · VBN Forskningsportal (Aalborg Universitet) · doi:10.5281/zenodo.4285373
Blondé, L., & Kalousis, A. (2021) · arXiv (Cornell University)
Panoramic Learning with A Standardized Machine Learning FormalismPreprint
Hu, Z., & Xing, E. P. (2021) · arXiv (Cornell University)
Trust, but Verify: Alleviating Pessimistic Errors in Model-Based Exploration
Czechowski, K., Odrzygóźdź, T., Izworski, M., Zbysiński, M., Kuciński, Ł., & Miłoś, P. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534062
Residual Overfit Method of ExplorationPreprint
McInerney, J., & Kallus, N. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.02919
“This is known as the white noise problem in reinforcement learning [23].”
Visualización de conocimiento: La arquitectónica
Martin, M. D. S. (2021) · El Servicio de Difusión de la Creación Intelectual (National University of La Plata) · doi:10.35537/10915/128076
2P013 H.pyloriから分泌される新規分泌TNF-α誘導タンパク質(Tip)のX線結晶構造解析(蛋白質 A) 構造)
鶴村, 俊., 菅沼雅美, 勝沼, 信., & 津下, 英. (2004) · 生物物理
Mounsif, M., Lengagne, S., Thuilot, B., & Adouane, L. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-3-030-92442-3_10
A curiosity model for artificial agents
Ribeiro, E., Ribeiro, R., & de Matos, D. M. (2017) · European Conference on Artificial Life · doi:10.7551/ecal_a_089
“In this sense, if we want an artificial agent to be able to learn in the same way that humans do, then it should be partially curiositydriven as well (Schmidhuber, 2010).”
Background(2018) · Elsevier eBooks · doi:10.1016/b978-0-12-812143-6.00028-x
High Performance Computing of Possible Minds
Ziesche, S., & Yampolskiy, R. V. (2019) · Natural Language Processing · doi:10.4018/978-1-7998-0951-7.ch066
An Examination of High School Students' Online Engagement in Mathematics Problems
Lim, W., Son, J., Gregson, S., & Kim, J. (2021) · IGI Global eBooks · doi:10.4018/978-1-7998-8047-9.ch053
Predictive HermeneuticsPreprint
Reason, S., & Rutten, T. (2020) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/tg8ym
Unsupervised detection of interesting discrete sequences using Bayesian surprisePreprint
McGarry, K., McDonald, S., & Button, D. (2022) · Research Square · doi:10.21203/rs.3.rs-1238817/v1
Creativity as an Interdisciplinary Competence of the Individual and of the Artificial Intelligence
Szulc, J. (2022) · E-learning · doi:10.34916/el.2022.14.11
Kamitani, Y. (2023) · Denshi Jouhou Tsuushin Gakkai Tsuushin Sosaieti magajin/B-plus/Denshi Jouhou Tsuushin Gakkai Tsuushin Sosaeti magajin · doi:10.1587/bplus.16.295
Survival Decisions in a Multidimensional WorldPreprint
Mobbs, D., Wise, T., Tashjian, S. M., Friston, K. J., & Headley, D. B. (2023) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/jkmpq
Autonomous learning in robotics
Wilmot, C. (2022) · Publication Server of Goethe University Frankfurt am Main (Goethe University Frankfurt) · doi:10.21248/gups.72114
Danesi, M. (2023) · Mathematics in mind · doi:10.1007/978-3-031-31582-4_3
Reinforcement Learning for Data Science
Barkan, J., Moran, M., & Gordon, G. (2023) · Springer eBooks · doi:10.1007/978-3-031-24628-9_24
Intelligence as a Measure of ConsciousnessPreprint
Ševo, I. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2309.00646
Bayesian partially observable reinforcement learning
Katt, S. (2023) · Digital Repository Service (Northeastern University) · doi:10.17760/d20486919
Leveling up fun: Learning progress, expectations, and success influence enjoyment in video gamesPreprint
Brändle, F., Wu, C. M., & Schulz, E. (2024) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/vg8dz · Cited by 1
Autoencoder Reconstruction Model for Long-Horizon Exploration
Yan, R., Wu, Y., Gan, Y., Yang, Y., Yu, Z., Liu, Z., Zhang, X., Liang, L., & Cai, Y. (2024) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn60899.2024.10650970 · Cited by 1
“Later works emphasized encouraging exploration in uncertain states by visiting states with low visit counts, but these methods still face challenges in complex environments and large-scale continuous spaces [13], [16], [29], [33], [37].”
BackgroundTraits Inference on Virtual Agents Driven by Cognitive Curiosity Models
Nagashima, K., & Morita, J. (2024) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/3687272.3688316
Zhang, S., Tian, Y., Liu, Q., & Wu, H. (2025) · eLife · doi:10.7554/elife.92892.3
Comparative Study on Curiosity with Attention, Memory and Empowerment
Duarte, F. F., Lau, N., Pereira, A., & Reis, L. P. (2025) · IEEE International Conference on Autonomous Robot Systems and Competitions · doi:10.1109/icarsc65809.2025.10970179
“Curiosity is a research area that aims to address these issues [2].”
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.002.0005
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.003.0015
Boredom as Cognitive Allostasis
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.003.0008 · Cited by 1
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.003.0012 · Cited by 1
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.003.0003
Conclusion: The Aesthetics of Boredom
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.003.0014
Introduction: Painful Thoughts
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.003.0001
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.002.0004
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.003.0011
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.003.0010
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.002.0006
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.002.0007
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.003.0013
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.003.0004
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.003.0007
Elpidorou, A. (2025) · Oxford University Press eBooks · doi:10.1093/9780197564363.003.0005
Merits of curiosity: a simulation studyPreprint
Gruaz, L., Modirshanechi, A., Becker, S., & Brea, J. (2025) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/evm9n_v4 · Cited by 1
Merits of curiosity: a simulation studyPreprint
Gruaz, L., Modirshanechi, A., Becker, S., & Brea, J. (2025) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/evm9n_v2 · Cited by 5
Merits of curiosity: a simulation studyPreprint
Gruaz, L., Modirshanechi, A., Becker, S., & Brea, J. (2025) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/evm9n_v3 · Cited by 1
Metadata
- Authors
- Schmidhuber, J.
- Affiliations
- Dalle Molle Institute for Artificial Intelligence Research (CH)
- Corresponding author
- Schmidhuber, Jürgen
- ORCID
- Schmidhuber, Jürgen
- Venue
- IEEE Transactions on Autonomous Mental Development
- Published
- 2010-09
- Volume
- 2
- Issue
- 3
- Pages
- 230-247
- ISSN
- 1943-0604 (ISSN-L)
- 1943-0612
- OpenAlex
- W2034806191
- Cited by
- 747
- References
- 126
- Citations by year
- 2026: 29 · 2025: 64 · 2024: 46 · 2023: 50 · 2022: 60 · 2021: 69 · 2020: 92 · 2019: 72 · 2018: 55 · 2017: 37 · 2016: 26 · 2015: 24 · 2014: 30 · 2013: 28 · 2012: 41
- FWCI
- 31.09
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Autonomous Mental Development (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Artificial Intelligence › Psychiatry, Mental Health, Neuroscience
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Creativity in Education and Neuroscience
- Keywords
- intrinsic motivation, creativity, fun, intrinsic rewards, active learning (machine learning), novelty seeking, surprise, pattern discovery, data compression, online prediction, autonomous agents, robots, aesthetics, humor, intelligence, limited computational resources, continuous-time formulation, discrete-time formulation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.