Professor Marcus Hutter
Areas of expertise
- Coding And Information Theory 080401
- Artificial Intelligence And Image Processing 0801
- Statistical Theory 010405
- Adaptive Agents And Intelligent Robotics 080101
- Pattern Recognition And Data Mining 080109
- Computation Theory And Mathematics 0802
- Philosophy 2203
- Particle Physics 020203
Research interests
Artificial intelligence, Bayesian statistics, theoretical computer science, machine learning, sequential decision theory, universal forecasting, algorithmic information theory, adaptive control, MDL, image processing, particle physics, philosophy of science.
See http://www.hutter1.net/ for details.
Biography
Marcus Hutter is Professor in the RSCS at the Australian National University in Canberra, Australia, and NICTA adjunct. He received his PhD and BSc in physics from the LMU in Munich and a Habilitation, MSc, and BSc in informatics from the TU Munich. Since 2000, his research at IDSIA and ANU is centered around the information-theoretic foundations of inductive reasoning and reinforcement learning, which has resulted in 100+ publications and several awards. His book "Universal Artificial Intelligence" (Springer, EATCS, 2005) develops the first sound and complete theory of AI. He also runs the Human Knowledge Compression Contest (50'000 Euro H-prize).
Publications
- Everitt, T, Hutter, M, Kumar, R et al. 2021, 'Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective', Synthese, vol. 198, pp. 1-33.
- Hutter, R & Hutter, M 2021, 'Chances and Risks of Artificial Intelligence-A Concept of Developing and Exploiting Machine Intelligence for Future Societies', Applied System Innovation, vol. 4, no. 2.
- Everitt, T, Lea, G & Hutter, M 2018, 'AGI safety literature review', 27th International Joint Conference on Artificial Intelligence, IJCAI 2018, ed. Jerome Lang, AAAI Press, USA, pp. 5441-5449.
- Everitt, T & Hutter, M 2018, 'Universal artificial intelligence: Practical agents and fundamental challenges', in H Abbass, J Scholz & D Reid (ed.), Foundations of Trusted Autonomy, Springer, Switzerland, pp. 15-46.
- Leike, J & Hutter, M 2018, 'On the computability of Solomonoff induction and AIXI', Theoretical Computer Science, vol. 716, pp. 28-49pp.
- Hutter, M 2018, 'Tractability of batch to sequential conversion', Theoretical Computer Science, vol. 733, pp. 71-82.
- Vellambi Ravisankar, B & Hutter, M 2018, 'Convergence of Binarized Context-tree Weighting for Estimating Distributions of Stationary Sources', 2018 IEEE International Symposium on Information Theory, ISIT 2018, IEEE, USA, pp. 731-735pp.
- Vellambi Ravisankar, B, Hutter, M & Cameron, O 2018, 'Universal Compression of Piecewise i.i.d. Sources', 2018 Data Compression Conference, DCC 2018, ed. Ali Bilgin, Michael W. Marcellin, Joan Serra-Sagrista, James A. Storer, IEEE, TBC, pp. 267-276.
- Lamont, S, Aslanides, J, Leike, J et al 2017, 'Generalised discount functions applied to a Monte-Carlo AL implementation', 16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017, ed. E Durfee, M Winikoff, K Larson & S Das, IFAAMAS (International Foundation for Autonomous Agents and Multiagent Systems), TBC, pp. 1589-1591.
- Wangberg, T, Boors, M, Carpenter Catt, E et al. 2017, 'A Game-Theoretic Analysis of the Off-Switch Game ', 10th International Conference on Artificial General Intelligence, AGI 2017, ed. T Everitt, B Goertzel & A Potapov, Springer, Cham, Switzerland, pp. 167-177pp.
- Martin, J, Hutter, M & Everitt, T 2017, 'Count-based exploration in feature space for reinforcement learning?', 26th International Joint Conference on Artificial Intelligence, IJCAI 2017, ed. C Sierra, International Joint Conferences on Artificial Intelligence, Australia, pp. 2471-2478.
- Leike, J, Lattimore, T, Orseau, L et al 2017, 'On Thompson sampling and asymptotic optimality', 26th International Joint Conference on Artificial Intelligence, IJCAI 2017, ed. C Sierra, International Joint Conferences on Artificial Intelligence, Australia, pp. 4889-4893.
- Aslanides, J, Leike, J & Hutter, M 2017, 'Universal reinforcement learning algorithms: Survey and experiments', 26th International Joint Conference on Artificial Intelligence, IJCAI 2017, ed. C Sierra, International Joint Conferences on Artificial Intelligence, Australia, pp. 1403-1410.
- Leike, J, Lattimore, T, Orseau, L et al 2016, 'Thompson Sampling is Asymptotically Optimal in General Environments', 32nd Conference on Uncertainty in Artificial Intelligence 2016, ed. Alexander Ihler and Dominik Janzing, AUAI Press, Canada, pp. 417-426pp.
- Everitt, T, Filan, D, Daswani, M et al 2016, 'Self-Modification of Policy and Utility Function in Rational Agents', International Conference on Artificial General Intelligence, AGI 2016, ed. B. Steunebrink, P Wang, B. Goertzel, Springer International Publishing AG, Switzerland, pp. 1-11.
- Everitt, T & Hutter, M 2016, 'Avoiding wireheading with value reinforcement learning', International Conference on Artificial General Intelligence, AGI 2016, ed. B. Steunebrink, P Wang, B. Goertzel, Springer International Publishing AG, Switzerland, pp. 12-22.
- Hutter, M 2016, 'Extreme state aggregation beyond Markov decision processes', Theoretical Computer Science, vol. 650, pp. 73-91.
- Fernando, B, Anderson, P, Hutter, M et al. 2016, 'Discriminative hierarchical rank pooling for activity recognition', IEEE Conference on Computer Vision and Pattern Recognition, 2016, IEEE, USA, pp. 1924-1932.
- Martin, J, Everitt, T & Hutter, M 2016, 'Death and suicide in universal artificial intelligence', International Conference on Artificial General Intelligence, AGI 2016, ed. B. Steunebrink, P Wang, B. Goertzel, Springer International Publishing AG, Switzerland, pp. 23-32.
- Filan, D, Leike, J & Hutter, M 2016, 'Loss Bounds and Time Complexity for Speed Priors', 19th International Conference on Artificial Intelligence and Statistics AISTATS 2016, JMLR - Journal of Machine Learning, USA, pp. 1394-1402.
- Leike, J & Hutter, M 2015, 'On the computability of AIXI', Conference on Uncertainty in Artificial Intelligence, UAI 2015, ed. Heskes T.Meila M., AUAI Press, TBC, pp. 464-473.
- Leike, J & Hutter, M 2015, 'Bad Universal Priors and Notions of Optimality', Conference on Learning Theory, COLT 2015, ed. Peter Grünwald, Elad Hazan, Satyen Kale, JMLR - Journal of Machine Learning, USA, pp. 1-16.
- Veness, J, Hutter, M, Orseau, L et al 2015, 'Online Learning of k-CNF Boolean Functions', International Joint Conference on Artificial Intelligence IJCAI 2015, ed. Qiang Yang, Michael Wooldridge, AAAI Press, Palo Alto, California, USA, pp. 3865-3873.
- Veness, J, Bellemare, M, Hutter, M et al 2015, 'Compress and control', Conference on Artificial Intelligence (AAAI 2015), ed. Q.Yang and M.Wolldridge, American Association for Artificial Intelligence (AAAI) Press, United States, pp. 3016--3023.
- Sunehag, P & Hutter, M 2015, 'Algorithmic Complexity', in James D Wright (ed.), International Encyclopedia of the Social & Behavioral Sciences (Second Edition), Elsevier, Oxford, pp. 534-538pp.
- Hutter, M 2013, To create a super-intelligence machine, start with an equation, pp. 4pp.
- Hutter, M 2009, 'Exact Non-Parametric Bayesian Inference on Infinite Trees', arXiv (e-archive for Pre-prints, author submits), vol. online, pp. 1-32.
- Lattimore, T & Hutter, M 2015, 'On Martin-Lof (Non-)Convergence of Solomonoff's Universal Mixture', Theoretical Computer Science, vol. 588, pp. 2-15.
- Jayawardena, S, Gould, S, Li, H et al 2015, 'Reliable Point Correspondences in Scenes Dominated by Highly Reflective and Largely Homogeneous Surfaces', 12th Asian Conference on Computer Vision, ACCV 2014, ed. H.Reid, I.Yang, Springer, TBC, pp. 659-674.
- Sunehag, P & Hutter, M 2015, 'Rationality, Optimism and Guarantees in General Reinforcement Learning', Journal of Machine Learning Research, vol. 16, pp. 1345-1390.
- Sunehag, P & Hutter, M 2015, 'Using Localization and Factorization to Reduce the Complexity of Reinforcement Learning', 8th Conference on Artificial General Intelligence AGI 2015, ed. Jordi Bieger, Ben Goertzel, Alexey Potapov, Springer International Publishing Switzerland, Switzerland, pp. 177-186.
- Everitt, T & Hutter, M 2015, 'Analytical Results on the BFS vs. DFS Algorithm Selection Problem. Part I: Tree Search', Australasian Joint Conference on Artificial Intelligence AI 2015, ed. B. Pfahringer and J Renz, Springer International Publishing AG, Switzerland, pp. 157-165.
- Everitt, T, Leike, J & Hutter, M 2015, 'Sequential extensions of causal and evidential decision theory', 4th International Conference on Algorithmic Decision Theory, ADT 2015, ed. Walsh T., Springer International Publishing Switzerland, TBC, pp. 205-221.
- Everitt, T & Hutter, M 2015, 'Analytical Results on the BFS vs. DFS Algorithm Selection Problem: Part II: Graph Search', Australasian Joint Conference on Artificial Intelligence AI 2015, ed. B. Pfahringer and J Renz, Springer International Publishing AG, Switzerland, pp. 166-178.
- Leike, J & Hutter, M 2015, 'On the computability of Solomonoff induction and knowledge-seeking', 26th International Conference on Algorithmic Learning Theory, ALT 2015, pp. 364-378.
- Leike, J & Hutter, M 2015, 'Solomonoff induction violates Nicod's criterion', 26th International Conference on Algorithmic Learning Theory, ALT 2015, pp. 349-363.
- Veness, J, Bellemare, M, Hutter, M et al 2015, 'Compress and control', Proc. 29th AAAI Conference on Artificial Intelligence, pages 3016-3023
- Alpcan, T, Everitt, T & Hutter, M 2014, 'Can we measure the difficulty of an optimization problem?', Information Theory Workshop (IFW) 2014, IEEE, USA, pp. 356 - 360.
- Lattimore, T & Hutter, M 2014, 'Near-optimal PAC bounds for discounted MDPs', Theoretical Computer Science, vol. 558, pp. 125-143.
- Sunehag, P & Hutter, M 2014, 'A Dual Process Theory of Optimistic Cognition', CogSci 2014 - 36th Annual Meeting of the Cognitive Science Society, ed. P Bello, M Guarini, M McShane, B Scassellati, Mindmodeling, online, pp. 2949-2954.
- Yang, D, Jayawardena, S, Gould, S et al 2014, 'Reflective Features Detection and Hierarchical Reflections Separation in Image Sequences', 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA), ed. Phung, S.L., Bouzerdoum, A., Ogunbona, P., Li, W., Wang, L., IEEE, USA, pp. 1-7.
- Daswani, M, Sunehag, P & Hutter, M 2014, 'Reinforcement Learning with Value Advice', Sixth Asian Conference on Machine Learning 2014, ed. Dinh Phung and Hang Li, Microtome Publishing, USA, pp. 299-314.
- Leike, J & Hutter, M 2014, 'Indefinitely oscillating martingales', 25th International Conference on Algorithmic Learning Theory, ALT 2014, ed. P Auer, A Clark,T Zeugmann, S Zilles, Springer, Slovenia, pp. 321-335.
- Lattimore, T & Hutter, M 2014, 'Asymptotics of Continuous Bayes for Non-i.i.d. Sources', arXiv (e-archive for Pre-prints, author submits), vol. 1411.2918v2.
- Everitt, T, Lattimore, T & Hutter, M 2014, 'Free Lunch for Optimisation under the Universal Distribution', 2014 IEEE Congress on Evolutionary Computation, CEC 2014, IEEE, China, pp. 167-174.
- Sunehag, P & Hutter, M 2014, 'Intelligence as inference or forcing Occam on the world', International Conference on Artificial General Intelligence, AGI 2014, ed. B Goertzel, L Orseau, J Snaider, Springer, Quebec City, Canada, pp. 186-195.
- Hutter, M 2014, 'Offline to Online Conversion', 25th International Conference on Algorithmic Learning Theory, ALT 2014, ed. P Auer, A Clark,T Zeugmann, S Zilles, Springer, Slovenia, pp. 230-244.
- Hutter, M 2014, 'Extreme State Aggregation beyond MDPs', 25th International Conference on Algorithmic Learning Theory, ALT 2014, ed. P Auer, A Clark,T Zeugmann, S Zilles, Springer, Slovenia, pp. 185-199.
- Lattimore, T & Hutter, M 2014, 'Bayesian reinforcement learning with exploration', 25th International Conference on Algorithmic Learning Theory, ALT 2014, ed. P Auer, A Clark,T Zeugmann, S Zilles, Springer, Slovenia, pp. 170-184.
- Lattimore, T & Hutter, M 2014, 'General time consistent discounting', Theoretical Computer Science, vol. 519, no. 30 January 2014, pp. 140-154.
- Daswani, M, Sunehag, P & Hutter, M 2014, 'Feature Reinforcement Learning: State of the Art', Proc. Workshops at the 28th AAAI Conference on Artificial Intelligence: Sequential Decision Making with Big Data, AAAI Press, Canada, pp. 2-5.
- Wood, I, Sunehag, P & Hutter, M 2013, '(Non-)Equivalence of Universal Priors', Lecture Notes in Artificial Intelligence, vol. LNAI 7070, pp. 417-425.
- Orseau, L, Lattimore, T & Hutter, M 2013, 'Universal Knowledge-Seeking Agents for Stochastic Environments', 24th International Conference on Algorithmic Learning Theory, ALT 2013, ed. S. Jain, R. Munos, F. Stephan and Th. Zeugmann, Springer Berlin, USA, pp. 146-160.
- Hutter, M, Lloyd, J, Ng, K et al 2013, 'Unifying Probability and Logic for Learning', 23rd International Joint Conference on Artificial Intelligence, IJCAI 2013, AAAI Press, USA, pp. 65-72.
- Lattimore, T, Hutter, M & Sunehag, P 2013, 'Concentration and Confidence for Discrete Bayesian Sequence Predictors', 24th International Conference on Algorithmic Learning Theory, ALT 2013, ed. S. Jain, R. Munos, F. Stephan and Th. Zeugmann, Springer Berlin, USA, pp. 324-338.
- Lattimore, T, Hutter, M & Sunehag, P 2013, 'The Sample-Complexity of General Reinforcement Learning', 30th International Conference on Machine Learning ICML 2013, MIT Press, USA, pp. 1-9.
- Hutter, M, Stephan, F, Vovk, V et al, eds, 2013, Guest Editors' Foreword.
- Sunehag, P & Hutter, M 2013, 'Learning Agents with Evolving Hypothesis Classes', 6th Conference on Artificial General Intelligence AGI-2013, ed. K.U. Kuhnberger, S. Rudolph, and P. Wang, Springer-Verlag Berlin Heidelberg, Ny, USA, pp. 150-159.
- Hutter, M, Lloyd, J, Ng, K et al 2013, 'Probabilities on Sentences in an Expressive Logic', Journal of Applied Logic, vol. 11, no. 4, pp. 386-420.
- Hutter, M 2013, 'Sparse Adaptive Dirichlet-Multinomial-like Processes', 26th Conference on Learning Theory, COLT 2013, ed. Shai Shalev-Shwartz and Ingo Steinwart, Conference Organising Committee, Princeton, NJ, pp. 1-28.
- Lattimore, T & Hutter, M 2013, 'On Martin-Lof (non-)convergence of Solomonoff's universal mixture', 10th International Conference on Theory and Applications of Models of Computation, TAMC 2013, Conference Organising Committee, Hong Kong, pp. 212-223.
- Daswani, M, Sunehag, P & Hutter, M 2013, 'Q-learning for history-based reinforcement learning', Journal of Machine Learning Research, vol. 29, pp. 213-228.
- Sanner, S & Hutter, M, eds, 2012, Recent Advances in Reinforcement Learning.
- Nguyen, P, Sunehag, P & Hutter, M 2012, 'Feature reinforcement learning in practice', European Workshop on Reinforcement Learning (EWRL 2011), Springer Berlin Heidelberg, Athens Greece, pp. 66-77.
- O'Neill, A, Hutter, M, Shao, W et al. 2012, 'Adaptive context tree weighting', Data Compression Conference (DCC 2012), Institute of Electrical and Electronics Engineers (IEEE Inc), Snowbird USA, pp. 317-326.
- Nguyen, P, Sunehag, P & Hutter, M 2012, 'Context tree maximizing reinforcement learning', AAAI Conference on Artificial Intelligence and the Innovative Applications of Artificial Intelligence Conference 2012, AAAI Press, Toronto Canada, pp. 1075-1082.
- Hutter, M, Veness, J, Ng, K et al 2012, 'Context tree switching', Data Compression Conference (DCC 2012), Institute of Electrical and Electronics Engineers (IEEE Inc), Snowbird USA, pp. 327-336.
- Lattimore, T & Hutter, M 2012, 'PAC bounds for discounted MDPs', International Conference on Algorithmic Learning Theory (ALT 2012), Springer, Lyon, pp. 320-334.
- Sunehag, P & Hutter, M 2012, 'Optimistic AIXI', Conference on Artificial General Intelligence (AGI 2012), Conference Organising Committee, Oxford, pp. 312-321.
- Veness, J, Sunehag, P & Hutter, M 2012, 'On ensemble techniques for AIXI approximation', Conference on Artificial General Intelligence (AGI 2012), Conference Organising Committee, Oxford, pp. 341-351.
- Sunehag, P & Hutter, M 2012, 'Optimistic agents are asymptotically optimal', Australasian Joint Conference on Artificial Intelligence (AI 2012), Conference Organising Committee, Sydney, NSW, pp. 15-26.
- Hutter, M 2012, 'One Decade of Universal Artificial Intelligence', in Pei Wang and Ben Goertzel (ed.), Theoretical Foundations of Artificial General Intelligence, Atlantis Press, Netherlands France, pp. 67-88.
- Sunehag, P, Shao, W & Hutter, M 2012, 'Coding of Non-Stationary Sources as a Foundation for Detecting Change Points and Outliers in Binary Time-Series', Australasian Data Mining Conference (AusDM 2012), Australian Computer Society Inc., Sydney Australia, pp. 1-6.
- Hutter, M 2012, 'Can Intelligence Explode?', Journal of Consciousness Studies, vol. 19, no. 1-2, pp. 143-166.
- Daswani, M, Sunehag, P & Hutter, M 2012, 'Feature Reinforcement Leaning using Looping Suffix Trees', European Workshop on Reinforcement Learning (EWRL 2012), JMLR - Journal of Machine Learning, Edinburgh, pp. 11-22.
- Yang, D, Gould, S & Hutter, M 2012, 'A Noise Tolerant Watershed Transformation with Viscous Force for Seeded Image Segmentation', Lecture Notes in Computer Science (LNCS), vol. 7724, pp. 775-789.
- Hutter, M 2011, 'Observer Localization in Multiverse Theories', Conference in Honour of Murray Gell-Mann's 80th Birthday, ed. H Fritzsch and K K Phua, World Scientific Publishing Company, Singapore, pp. 638-645.
- Wood, I, Sunehag, P & Hutter, M 2011, '(Non-)Equivalence of Universal Priors', Solomonoff Memorial Conference 2011, Springer, Berlin Germany, pp. 1-10.
- Lattimore, T, Hutter, M & Gavane, V 2011, 'Universal Prediction of Selected Bits', International Conference on Algorithmic Learning Theory (ALT 2011), ed. Jyrki Kivinen, Csaba Szepesvári, Esko Ukkonen and Thomas Zeugmann, Springer, Heidelberg Germany, pp. 262-276.
- Lattimore, T & Hutter, M 2011, 'Time Consistent Discounting', International Conference on Algorithmic Learning Theory (ALT 2011), ed. Jyrki Kivinen, Csaba Szepesvári, Esko Ukkonen and Thomas Zeugmann, Springer, Heidelberg Germany, pp. 383-397.
- Veness, J, Ng, K, Hutter, M et al 2011, 'A Monte-Carlo AIXI approximation', Journal of Artificial Intelligence Research, vol. 40, pp. 95-142.
- Rathmanner, S & Hutter, M 2011, 'A philosophical treatise of universal induction', Entropy, vol. 13, no. 6, pp. 1076-1136.
- Sunehag, P & Hutter, M 2011, 'Axioms for Rational Reinforcement Learning', International Conference on Algorithmic Learning Theory (ALT 2011), ed. Jyrki Kivinen, Csaba Szepesvári, Esko Ukkonen and Thomas Zeugmann, Springer, Heidelberg Germany, pp. 338-352.
- Sunehag, P & Hutter, M 2011, 'Principles of Solomonoff Induction and AIXI', Solomonoff Memorial Conference 2011, Springer, Berlin Germany, p. 14.
- Lattimore, T & Hutter, M 2011, 'Asymptotically Optimal Agents', International Conference on Algorithmic Learning Theory (ALT 2011), ed. Jyrki Kivinen, Csaba Szepesvári, Esko Ukkonen and Thomas Zeugmann, Springer, Heidelberg Germany, pp. 368-382.
- Hutter, M & Goertzel, B 2011, 'Report on the third conference on artificial general intelligence', AI Magazine, vol. 31, no. 3, pp. 123-124.
- Hutter, M 2011, 'Algorithmic Randomness as Foundation of Inductive Reasoning and Artificial Intelligence', Chapter 12 in Randomness through Computation: Some Answers, More Questions (2011) 159-169
- Jayawardena, S, Hutter, M & Brewer, N 2011, 'A Novel Illumination-Invariant Loss for Monocular 3D Pose Estimation', Digital Image Computing: Techniques and Applications, IEEE Communications Society, p. 37-44
- Jayawardena, S, Yang, D & Hutter, M 2011, '3D Model Assisted Image Segmentation', Digital Image Computing: Techniques and Applications, IEEE Communications Society, p. 51.
- Lattimore, T & Hutter, M 2011, 'No free lunch versus Occam's Razor in supervised learning', Ray Solomonoff 85th Memorial Conference on Algorithmic Probability and Friends: Bayesian Prediction and Artificial Intelligence, Conference Organising Committee, Melbourne, VIC, pp. 223-235.
- Jayawardena, K, Hutter, M & Brewer, N 2010, 'Featureless 2D-3D pose estimation by minimising an illumination-invariant loss', 25th International Conference of Image and Vision Computing New Zealand, IVCNZ 2010, IEEE, Queenstown.
- Hutter, M 2010, 'Editors' introduction', International Conference on Algorithmic Learning Theory (ALT 2010), ed. Conference Program Committee, Springer, Berlin, Heidelberg, pp. 1-10.
- Hutter, M & Tran, M 2010, 'Model selection with the Loss Rank Principle', Computational Statistics and Data Analysis, vol. 54, no. 5, pp. 1288-1306.
- Veness, J, Ng, K, Hutter, M et al 2010, 'Reinforcement Learning via AIXI Approximation', 24th AAAI Conference on Artificial Intelligence and the 22nd Innovative Applications of Artificial Intelligence Conference, AAAI-10 /IAAI-10, AAAI Press, Georgia USA, p. 7.
- Hutter, M, Stephan, F, Vovk, V et al, eds, 2010, Algorithmic Learning Theory, Springer, Germeny.
- Hutter, M 2010, 'A Complete Theory of Everything (will be subjective)', Algorithms, vol. 3, no. 4, pp. 329-350.
- Rancoita, P, Hutter, M, Bertoni, F et al 2010, 'An integrated Bayesian analysis of LOH and copy number data', BMC Bioinformatics, vol. 11, no. 321, p. 18.
- Sunehag, P & Hutter, M 2010, 'Consistency of Feature Markov Processes', International Conference on Algorithmic Learning Theory (ALT 2010), ed. Conference Program Committee, Springer, Berlin, Heidelberg, p. 15.
- Baum, E, Hutter, M & Kitzelmann, E, eds, 2010, Artificial General Intelligence (Vol10), Atlantis Press, Lugano, Switzerland.
- Hutter, M 2010, 'Universal Learning Theory', in Claude Sammut & Geoffrey I.Webb (ed.), Encyclopedia of Machine Learning, Springer, New York, pp. 1001-1008pp.
- Hutter, M, Merkle, W & Vitanyi, P, eds, 2006, Kolmogorov Complexity and Applications (06051 Abstracts Collection), Schloss Dagstuhl - Leibniz-Zentrum für Informatik, online.
- Kwee, I, Hutter, M & Schmidhuber, J 2001, 'Market-based Reinforcement Learning in Partially Observable Worlds', Artificial Neural Networks - ICANN 2001, ed. G. Dorffner, H. Bischof and K. Hornik, Springer-Verlag Berlin Heidelberg, Berlin Heidelberg, pp. 865-873.
- Hutter, M 2001, 'Universal sequential decisions in unknown environments', Fifth European Workshop on Reinforcement Learning, ed. Marco A. Wiering, Onderwijsinstituut CKI, Utrecht, pp. 25-26.
- Kwee, I, Hutter, M & Schmidhuber, J 2001, 'Gradient-based Reinforcement Planning in Policy-Search Methods', Fifth European Workshop on Reinforcement Learning, ed. Marco A. Wiering, Onderwijsinstituut CKI, Utrecht, pp. 27-29.
- Hutter, M 2009, 'Feature Markov Decision Processes', Conference on Artificial General Intelligence (AGI 2009), ed. B. Goertzel, P. Hitzler, M. Hutter, Atlantis Press, Arlington, Virginia USA, pp. 61-66.
- Hutter, M 2009, 'Feature dynamic Bayesian networks', Conference on Artificial General Intelligence (AGI 2009), ed. B. Goertzel, P. Hitzler, M. Hutter, Atlantis Press, Arlington, Virginia USA, pp. 67-73.
- Hutter, M 2009, 'Discrete MDL predicts in total variation', Conference on Advances in Neural Information Processing Systems (NIPS 2009), ed. Y. Bengio, D. Schuurmans, J. Lafferty, C. Williams, A. Culotta, MIT Press, Vancouver, Canada, pp. 817-825.
- Hutter, M & Brewer, N 2009, 'Matching 2-D ellipses to 3-D circles with application to vehicle pose identification', International Image and Vision Computing New Zealand Conference (IVCNZ 2009), ed. Conference Program Committee, Institute of Electrical and Electronics Engineers (IEEE Inc), Piscataway USA, pp. 153-158.
- Goertzel, B, Hitzler, P & Hutter, M, eds, 2009, Artificial General Intelligence, Atlantis Press, Paris, France.
- Zhang, K, Hutter, M & Jin, H 2009, 'A New Local Distance-based Outlier Detection Approach for Scattered Real-World Data', Pacific Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2009), ed. T Theeramunkong et al, Springer, Thailand, pp. 813-822.
- Rancoita, P, Hutter, M, Bertoni, F et al 2009, 'Bayesian Joint Estimation of CN and LOH Aberrations', International Workshop on Practical Applications of Computational Biology & Bioinformatics (IWPACBB 2009), ed. S Omatu et al, Springer, Spain, pp. 1109-1117.
- Hutter, M 2009, 'Practical robust estimators for the imprecise Dirichlet model', International Journal of Approximate Reasoning, vol. 50, no. 2, pp. 231-242.
- Hutter, M & Servedio, R 2009, 'Algorithmic Learning Theory: Preface', Theoretical Computer Science, vol. 410, no. 19, p. 1747.
- Piatti, A, Zaffalon, M, Trojani, F et al 2009, 'Limits of learning about a categorical latent variable under prior near-ignorance', International Journal of Approximate Reasoning, vol. 50, no. 4, pp. 597-611.
- Hutter, M 2009, 'Feature Reinforcement Learning: Part 1. Unstructured MDPs', Journal of Artificial General Intelligence, vol. 1, pp. 3-24.
- Hutter, M 2009, 'Open Problems in Universal Induction & Intelligence', Algorithms, vol. 3, no. 2, pp. 879-906.
- Rancoita, P, Hutter, M, Bertoni, F et al 2009, 'Bayesian DNA copy number analysis', BMC Bioinformatics, vol. 10, no. 10, pp. 1-19.
- Rancoita, P & Hutter, M 2009, mBPCR: A Package for DNA Copy Number Profile Estimation, tbc.
- Hutter, M 2008, 'Algorithmic complexity', Scholarpedia, vol. 3, no. 1, p. 2573.
- Ryabko, D & Hutter, M 2008, 'On the possibility of learning in reactive environments with arbitrary dependence', Theoretical Computer Science, vol. 405, no. 3, pp. 274-284.
- Ryabko, D & Hutter, M 2008, 'Predicting non-stationary processes', Applied Mathematics Letters, vol. 21, no. 5, pp. 477-482.
- Hingee, K & Hutter, M 2008, 'Equivalence of probabilistic tournament and polynomial ranking selection', Congress on Evolutionary Computation (CEC 2008), ed. Zbigniew Michalewicz, Robert G. Reynolds, Institute of Electrical and Electronics Engineers (IEEE Inc), Hong Kong, pp. 564-571.
- Hutter, M & Legg, S 2009, 'Temporal difference updating without a learning rate', Conference on Advances in Neural Information Processing Systems (NIPS 2007), ed. Platt, John C., Koller, Daphne, Singer, Yoram and Roweis, Sam, MIT Press, Vancouver Canada, pp. 705-712.
- Ryabko, D & Hutter, M 2007, 'On sequence predictions for arbitrary measures', IEEE International Symposium on Information Theory ISIT 2007, Institute of Electrical and Electronics Engineers (IEEE Inc), France, pp. 2346-2350.
- Hutter, M 2007, 'The loss rank principle for model selection', in N.H. Bshouty, C. Gentile (ed.), Learning Theory, Springer, Berlin, Germany, pp. 589-603.
- Hutter, M 2007, 'Algorithmic information theory', Scholarpedia, vol. 2, no. 3, p. 2519.
- Legg, S & Hutter, M 2007, 'Tests of machine intelligence', in M. Lungarella, F. Iida, J. Bongard, R. Pfeifer (ed.), 50 Years of Artificial Intelligence, Springer, Berlin, Germany, pp. 232-242.
- Hutter, M, Legg, S & Vitanyi, P 2007, 'Algorithmic probability', Scholarpedia, vol. 2, no. 8, p. 2572.
- Legg, S & Hutter, M 2007, 'Universal intelligence: A definition of machine intelligence', Minds and Machines: journal for artificial intelligence, philosophy and cognitive sciences, vol. 17, no. 4, pp. 391-444.
- Hutter, M 2007, 'Exact Bayesian regression of piecewise constant functions', Bayesian Analysis, vol. 2, no. 4, pp. 635-664.
- Hutter, M, Servedio, R & Takimoto, E 2007, 'Algorithmic learning theory', in M. Hutter, R.A. Servedio, E. Takimoto (ed.), Algorithmic Learning Theory Proceedings, Springer, Berlin, Germany, pp. 1-8.
- Legg, S & Hutter, M 2007, 'A collection of definitions of intelligence', in Ben Goertzel, Pei Wang (ed.), Advances in Artificial General Intelligence: Concepts, Architectures and Algorithms, vol 157, IOS Press, UK, pp. 17-24.
- Hutter, M 2007, 'On universal prediction and Bayesian confirmation', Theoretical Computer Science, vol. 384, pp. 33-48.
- Hutter, M & Muchnik, A 2007, 'On semimeasures predicting Martin-Lof random sequences', Theoretical Computer Science, vol. 382, no. 3, pp. 247-261.
- Hutter, M 2007, 'Bayesian regression of piecewise constant functions', in JM Bernardo, MJ Bayarri, JO Berger, AP Dawid, D Heckerman, AFM Smith, M West (ed.), Bayesian Statistics 8, Oxford University Press, UK, pp. 607-612.
- Chernov, A, Hutter, M & Schmidhuber, J 2007, 'Algorithmic complexity bounds on future prediction errors', Information and Computation, vol. 205, no. 2, pp. 242-261.
- Hutter, M 2007, 'Universal algorithmic intelligence: A mathematical top-down approach', in B. Goertzel, C. Pennachin (ed.), Artificial General Intelligence, Springer, Berlin, Germany, pp. 227-290.
- Zhumatiy, V, Gomez, F, Hutter, M et al 2006, 'Metric state space reinforcement learning for a vision-capable mobile robot', in T. Aria, R. Pfeifer, T. Balch, H. Yokoi (ed.), Intelligent Autonomous Systems 9: proceedings of the 9th international conference on intelligent autonomous systems, Tokyo 2006, IOS Press, Amsterdam, The Netherlands, pp. 272-281.
- Hutter, M 2006, 'On generalised computable universal priors and their convergence', Theoretical Computer Science, vol. 364, no. 1, pp. 27-41.
- Ryabko, D & Hutter, M 2006, 'Asymptotic learnability of reinforcement problems with arbitrary dependence', International Conference on Algorithmic Learning Theory (ALT 2006), ed. Jose L Balcazar, Phillip M Long, Frank Stephen, Springer, Berlin, Germany, pp. 334-347.
- Legg, S & Hutter, M 2006, 'A formal measure of machine intelligence', Annual Machine Learning Conference of Belgium and The Netherlands (Benelearn 2006), ed. Y. Saeys, E. Tsiporova, B. DeBaets, Y. Van dePeer, Ghent University, Ghent, Belgium, pp. 73-80.
- Hutter, M & Legg, S 2006, 'Fitness uniform optimisation', IEEE Transactions on Evolutionary Computation, vol. 10, no. 5, pp. 568-589.
- Poland, J & Hutter, M 2006, 'MDL convergence speed for Bernoulli sequences', Statistics and Computing, vol. 16, no. 2, pp. 161-175.
- Hutter, M 2006, 'General discounting versus average reward', International Conference on Algorithmic Learning Theory (ALT 2006), ed. Jose L Balcazar, Phillip M Long, Frank Stephen, Springer, Berlin, Germany, pp. 244-258.
- Poland, J & Hutter, M 2006, 'Universal learning of repeated matrix games', Annual Machine Learning Conference of Belgium and The Netherlands (Benelearn 2006), ed. Y. Saeys, E. Tsiporova, B. DeBaets, Y. Van dePeer, Ghent University, Ghent, Belgium, pp. 7-14.
- Hutter, M 2006, 'On the foundations of universal sequence prediction', International Conference on Theory and Applications of Models of Computation (TAMC 2006), ed. Jin-Yi Cai, S. Barry Cooper, Angsheng Li, Springer, Berlin, Germany, pp. 408-420.
- Poland, J & Hutter, M 2005, 'Asymptotics of discrete (MDL) for online prediction', IEEE Transactions on Information Theory, vol. 51, no. 11, pp. 3780-3795.
- Hutter, M & Poland, J 2005, 'Adaptive Online Prediction by Following the Perturbed Leader', Journal of Machine Learning Research, vol. 6, no. April, pp. 639-660.
- Zaffalon, M & Hutter, M 2005, 'Robust inference of trees', Annals of Mathematics and Artificial Intelligence, vol. 45, no. 1-2, pp. 215-239.
- Poland, J & Hutter, M 2005, 'Strong Asymptotic Assertions for Discrete {MDL} in Regression and Classification', Annual Machine Learning Conference of Belgium and The Netherlands (Benelearn 2005), ed. M. van Otterlo, M. Poel, A. Nijholt, University of Twente, Enschede, pp. 67-72.
- Hutter, M 2005, 'Fast Non-Parametric Bayesian Inference on Infinite Trees', International Conference on Artificial Intelligence and Statistics (AISTATS 2005), ed. Robert Cowell, Zoubin Ghahramani, Society for Artificial Intelligence and Statistics, Barbados, pp. 144-151.
- Legg, S & Hutter, M 2005, 'Fitness uniform deletion: A simple way to preserve diversity', Genetic and Evolutionary Computation Conference (GECCO 2005), ed. Hans-Georg Beyer, Unq-May O'Reilly, Association for Computing Machinery Inc (ACM), Washington DC, pp. 1271-1278.
- Hutter, M & Zaffalon, M 2005, 'Distribution of Mutual Information from Complete and Incomplete Data', Computational Statistics and Data Analysis, vol. 48, no. 3, pp. 633-657.
- Hutter, M 2005, Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability, Springer, Berlin, Germany.
- Chernov, A & Hutter, M 2005, 'Monotone conditional complexity bounds on future prediction errors', International Conference on Algorithmic Learning Theory (ALT 2005), ed. S. Jain, H.U. Simon, E. Tomita, Springer, Berlin, Germany, pp. 414-428.
- Poland, J & Hutter, M 2005, 'Defensive universal learning with experts', International Conference on Algorithmic Learning Theory (ALT 2005), ed. S. Jain, H.U. Simon, E. Tomita, Springer, Berlin, Germany, pp. 356-370.
- Legg, S & Hutter, M 2005, 'A universal measure of intelligence for artificial agents', International Joint Conference on Artificial Intelligence (IJCAI 2005), ed. Leslie P. Kaelbling, Alessandro Saffiotti, AAAI Press, Edinburgh, Scotland, pp. 1509-1510.
- Poland, J & Hutter, M 2005, 'Master Algorithms for Active Experts Problems based on Increasing Loss Values', Annual Machine Learning Conference of Belgium and The Netherlands (Benelearn 2005), ed. M. van Otterlo, M. Poel, A. Nijholt, University of Twente, Enschede, pp. 59-66.
- Legg, S, Hutter, M & Kumar, A 2004, 'Tournament versus Fitness Uniform Selection', Congress on Evolutionary Computation (CEC 2004), Institute of Electrical and Electronics Engineers (IEEE Inc), USA, pp. 2144-2151.
- Hutter, M & Muchnik, A 2004, 'Universal Convergence of Semimeasures on Individual Random Sequences', International Conference on Algorithmic Learning Theory (ALT 2004), ed. S. Ben-David, J. Case, A. Maruoka, Springer, Padova, Italy, pp. 234-248.
- Hutter, M & Poland, J 2004, 'Prediction with Expert Advice by Following the Perturbed Leader for General Weights', International Conference on Algorithmic Learning Theory (ALT 2004), ed. S. Ben-David, J. Case, A. Maruoka, Springer, Padova, Italy, pp. 279-293.
- Poland, J & Hutter, M 2004, 'Convergence of Discrete MDL for Sequential Prediction', Annual Conference on Computational Learning Theory (COLT 2004), ed. J. Shawe-Taylor, Y. Singer, Springer, Germany, pp. 300-314.
- Poland, J & Hutter, M 2004, 'On the Convergence Speed of MDL Predictions for Bernoulli Sequences', International Conference on Algorithmic Learning Theory (ALT 2004), ed. S. Ben-David, J. Case, A. Maruoka, Springer, Padova, Italy, pp. 294-308.
- Hutter, M 2003, 'On the Existence and Convergence of Computable Universal Priors', International Conference on Algorithmic Learning Theory (ALT 2003), ed. Ricard Gavalda et al, Springer, Germany, pp. 298-312.
- Hutter, M & Zaffalon, M 2003, 'Bayesian Treatment of Incomplete Discrete Data applied to Mutual Information and Feature Selection', German Conference on Artificial Intelligence (KI 2003), ed. A Gunter, R Kruse, B Neumann, Springer, Germany, pp. 396-406.
- Hutter, M 2003, 'Sequence Prediction based on Monotone Complexity', 16th Annual Conference on Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003, ed. Bernhard Schoelkopf, Manfred Warmuth, Springer, Berlin, pp. 506-521.
- Hutter, M 2003, 'An Open Problem Regarding the Convergence of Universal A Priori Probability', 16th Annual Conference on Learning Theory and 7th Kernel Workshop, COLT/Kernel 2003, ed. Bernhard Schoelkopf, Manfred Warmuth, Springer, Berlin, pp. 738-740.
- Hutter, M 2003, 'Robust Estimators under the Imprecise Dirichlet Model', International Symposium on Imprecise Probabilities and Their Application (ISIPTA 2003), ed. Jean-Marc Bernard and et al, Carleton Scientific, Switzerland, pp. 274-289.
- Hutter, M 2003, 'Optimality of universal Bayesian sequence prediction for general loss and alphabet', Journal of Machine Learning Research, vol. 4, pp. 971-1000.
- Hutter, M 2003, 'Convergence and loss bounds for Bayesian sequence prediction', IEEE Transactions on Information Theory, vol. 49, no. 8, pp. 2061-2067.
- Hutter, M 2002, 'Self-optimizing and Pareto-optimal policies in general environments based on Bayes-mixtures', Annual Conference on Computational Learning Theory (COLT 2002), ed. J. Kivinen, R.H. Sloan, Springer, Berlin, pp. 364-379.
- Hutter, M 2002, 'The fastest and shortest algorithm for all well-defined problems', International Journal of Foundations of Computer Science, vol. 13, no. 3, pp. 431-443.
- Hutter, M 2001, 'General loss bounds for universal sequence prediction', International Conference on Machine Learning (ICML 2001), ed. Carla E. Brodley & Andrea Pohoreckyj Danyluk, Morgan Kauffman Publishers, Williamstown, MA, pp. 210-217.
- Hutter, M 2001, 'Towards a Universal Theory of Artificial intelligence Based on Algorithmic Probability and Sequential Decisiions', 12th European Conference on Machine Learning, ed. Luc de Raedt and Peter Flach, Springer-Verlag Berlin Heidelberg, Berlin Heidelberg, pp. 226-238.
Projects and Grants
Grants information is drawn from ARIES. To add or update Projects or Grants information please contact your College Research Office.
- Unifying Foundations for Intelligent Agents (Primary Investigator)
- Feature Reinforcement Learning (Primary Investigator)
- From Universal Induction to Intelligent Systems (Primary Investigator)