Hutter, Marcus

91 publications

UAI 2025 RL, but Don’t Do Anything I Wouldn’t Do Michael K. Cohen, Marcus Hutter, Yoshua Bengio, Stuart Russell

NeurIPS 2025 Understanding Prompt Tuning and In-Context Learning via Meta-Learning Tim Genewein, Li Kevin Wenliang, Jordi Grau-Moya, Anian Ruoss, Laurent Orseau, Marcus Hutter

ICML 2024 Distributional Bellman Operators over Mean Embeddings Li Kevin Wenliang, Gregoire Deletang, Matthew Aitchison, Marcus Hutter, Anian Ruoss, Arthur Gretton, Mark Rowland

AAAI 2024 Dynamic Knowledge Injection for AIXI Agents Samuel Yang-Zhao, Kee Siong Ng, Marcus Hutter

ICLR 2024 Language Modeling Is Compression Gregoire Deletang, Anian Ruoss, Paul-Ambroise Duquenne, Elliot Catt, Tim Genewein, Christopher Mattern, Jordi Grau-Moya, Li Kevin Wenliang, Matthew Aitchison, Laurent Orseau, Marcus Hutter, Joel Veness

ICML 2024 Learning Universal Predictors Jordi Grau-Moya, Tim Genewein, Marcus Hutter, Laurent Orseau, Gregoire Deletang, Elliot Catt, Anian Ruoss, Li Kevin Wenliang, Christopher Mattern, Matthew Aitchison, Joel Veness

ICML 2023 Atari-5: Distilling the Arcade Learning Environment Down to Five Games Matthew Aitchison, Penny Sweetser, Marcus Hutter

ICLR 2023 Evaluating Representations with Readout Model Switching Yazhe Li, Jorg Bornschein, Marcus Hutter

IJCAI 2023 Levin Tree Search with Context Models Laurent Orseau, Marcus Hutter, Levi H. S. Lelis

ICML 2023 Memory-Based Meta-Learning on Non-Stationary Distributions Tim Genewein, Gregoire Deletang, Anian Ruoss, Li Kevin Wenliang, Elliot Catt, Vincent Dutordoir, Jordi Grau-Moya, Laurent Orseau, Marcus Hutter, Joel Veness

ICLR 2023 Neural Networks and the Chomsky Hierarchy Gregoire Deletang, Anian Ruoss, Jordi Grau-Moya, Tim Genewein, Li Kevin Wenliang, Elliot Catt, Chris Cundy, Marcus Hutter, Shane Legg, Joel Veness, Pedro A Ortega

NeurIPSW 2023 Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models Amal Rannen-Triki, Jorg Bornschein, Razvan Pascanu, Alexandre Galashov, Michalis Titsias, Marcus Hutter, András György, Yee Whye Teh

NeurIPS 2023 Self-Predictive Universal AI Elliot Catt, Jordi Grau-Moya, Marcus Hutter, Matthew Aitchison, Tim Genewein, Grégoire Delétang, Kevin Li, Joel Veness

ICLR 2023 Sequential Learning of Neural Networks for Prequential MDL Jorg Bornschein, Yazhe Li, Marcus Hutter

AISTATS 2023 Universal Agent Mixtures and the Geometry of Intelligence Samuel Allen Alexander, David Quarel, Len Du, Marcus Hutter

JMLR 2022 Fully General Online Imitation Learning Michael K. Cohen, Marcus Hutter, Neel Nanda

ICMLW 2022 Improved Generalization Bounds for Transfer Learning via Neural Collapse Tomer Galanti, András György, Marcus Hutter

ICLR 2022 On the Role of Neural Collapse in Transfer Learning Tomer Galanti, András György, Marcus Hutter

ICML 2021 Counterfactual Credit Assignment in Model-Free Reinforcement Learning Thomas Mesnard, Theophane Weber, Fabio Viola, Shantanu Thakoor, Alaa Saade, Anna Harutyunyan, Will Dabney, Thomas S Stepleton, Nicolas Heess, Arthur Guez, Eric Moulines, Marcus Hutter, Lars Buesing, Remi Munos

AAAI 2021 Exact Reduction of Huge Action Spaces in General Reinforcement Learning Sultan Javed Majeed, Marcus Hutter

AAAI 2021 Gated Linear Networks Joel Veness, Tor Lattimore, David Budden, Avishkar Bhoopchand, Christopher Mattern, Agnieszka Grabska-Barwinska, Eren Sezener, Jianan Wang, Peter Toth, Simon Schmitt, Marcus Hutter

NeurIPS 2020 A Combinatorial Perspective on Transfer Learning Jianan Wang, Eren Sezener, David Budden, Marcus Hutter, Joel Veness

AAAI 2020 Asymptotically Unambitious Artificial General Intelligence Michael K. Cohen, Badri N. Vellambi, Marcus Hutter

NeurIPS 2020 Logarithmic Pruning Is All You Need Laurent Orseau, Marcus Hutter, Omar Rivasplata

NeurIPS 2020 Online Learning in Contextual Bandits Using Gated Linear Networks Eren Sezener, Marcus Hutter, David Budden, Jianan Wang, Joel Veness

COLT 2020 Pessimism About Unknown Unknowns Inspires Conservatism Michael K. Cohen, Marcus Hutter

IJCAI 2019 A Strongly Asymptotically Optimal Agent in General Environments Michael K. Cohen, Elliot Catt, Marcus Hutter

IJCAI 2019 Conditions on Features for Temporal Difference-like Methods to Converge Marcus Hutter, Samuel Yang-Zhao, Sultan Javed Majeed

AAAI 2019 Performance Guarantees for Homomorphisms Beyond Markov Decision Processes Sultan Javed Majeed, Marcus Hutter

IJCAI 2018 AGI Safety Literature Review Tom Everitt, Gary Lea, Marcus Hutter

IJCAI 2018 On Q-Learning Convergence for Non-Markov Decision Processes Sultan Javed Majeed, Marcus Hutter

IJCAI 2017 Count-Based Exploration in Feature Space for Reinforcement Learning Jarryd Martin, Suraj Narayanan Sasikumar, Tom Everitt, Marcus Hutter

IJCAI 2017 On Thompson Sampling and Asymptotic Optimality Jan Leike, Tor Lattimore, Laurent Orseau, Marcus Hutter

IJCAI 2017 Universal Reinforcement Learning Algorithms: Survey and Experiments John Aslanides, Jan Leike, Marcus Hutter

CVPR 2016 Discriminative Hierarchical Rank Pooling for Activity Recognition Basura Fernando, Peter Anderson, Marcus Hutter, Stephen Gould

AISTATS 2016 Loss Bounds and Time Complexity for Speed Priors Daniel Filan, Jan Leike, Marcus Hutter

UAI 2016 Thompson Sampling Is Asymptotically Optimal in General Environments Jan Leike, Tor Lattimore, Laurent Orseau, Marcus Hutter

COLT 2015 Bad Universal Priors and Notions of Optimality Jan Leike, Marcus Hutter

AAAI 2015 Compress and Control Joel Veness, Marc G. Bellemare, Marcus Hutter, Alvin Chua, Guillaume Desjardins

UAI 2015 On the Computability of AIXI Jan Leike, Marcus Hutter

ALT 2015 On the Computability of Solomonoff Induction and Knowledge-Seeking Jan Leike, Marcus Hutter

IJCAI 2015 Online Learning of K-CNF Boolean Functions Joel Veness, Marcus Hutter, Laurent Orseau, Marc G. Bellemare

JMLR 2015 Rationality, Optimism and Guarantees in General Reinforcement Learning Peter Sunehag, Marcus Hutter

ALT 2015 Solomonoff Induction Violates Nicod's Criterion Jan Leike, Marcus Hutter

ALT 2014 Bayesian Reinforcement Learning with Exploration Tor Lattimore, Marcus Hutter

ALT 2014 Extreme State Aggregation Beyond MDPs Marcus Hutter

ALT 2014 Indefinitely Oscillating Martingales Jan Leike, Marcus Hutter

ALT 2014 Offline to Online Conversion Marcus Hutter

ACML 2014 Reinforcement Learning with Value Advice Mayank Daswani, Peter Sunehag, Marcus Hutter

ALT 2013 Concentration and Confidence for Discrete Bayesian Sequence Predictors Tor Lattimore, Marcus Hutter, Peter Sunehag

ACML 2013 Q-Learning for History-Based Reinforcement Learning Mayank Daswani, Peter Sunehag, Marcus Hutter

COLT 2013 Sparse Adaptive Dirichlet-Multinomial-like Processes Marcus Hutter

ICML 2013 The Sample-Complexity of General Reinforcement Learning Tor Lattimore, Marcus Hutter, Peter Sunehag

ALT 2013 Universal Knowledge-Seeking Agents for Stochastic Environments Laurent Orseau, Tor Lattimore, Marcus Hutter

AAAI 2012 Context Tree Maximizing Phuong Nguyen, Peter Sunehag, Marcus Hutter

ALT 2012 PAC Bounds for Discounted MDPs Tor Lattimore, Marcus Hutter

JAIR 2011 A Monte-Carlo AIXI Approximation Joel Veness, Kee Siong Ng, Marcus Hutter, William T. B. Uther, David Silver

ALT 2011 Asymptotically Optimal Agents Tor Lattimore, Marcus Hutter

ALT 2011 Axioms for Rational Reinforcement Learning Peter Sunehag, Marcus Hutter

ALT 2011 Time Consistent Discounting Tor Lattimore, Marcus Hutter

ALT 2011 Universal Prediction of Selected Bits Tor Lattimore, Marcus Hutter, Vaibhav Gavane

ALT 2010 Algorithmic Learning Theory, 21st International Conference, ALT 2010, Canberra, Australia, October 6-8, 2010. Proceedings Marcus Hutter, Frank Stephan, Vladimir Vovk, Thomas Zeugmann

ALT 2010 Consistency of Feature Markov Processes Peter Sunehag, Marcus Hutter

ALT 2010 Editors' Introduction Marcus Hutter, Frank Stephan, Vladimir Vovk, Thomas Zeugmann

AAAI 2010 Reinforcement Learning via AIXI Approximation Joel Veness, Kee Siong Ng, Marcus Hutter, David Silver

NeurIPS 2009 Discrete MDL Predicts in Total Variation Marcus Hutter

ALT 2007 Algorithmic Learning Theory, 18th International Conference, ALT 2007, Sendai, Japan, October 1-4, 2007, Proceedings Marcus Hutter, Rocco A. Servedio, Eiji Takimoto

ALT 2007 Editors' Introduction Marcus Hutter, Rocco A. Servedio, Eiji Takimoto

NeurIPS 2007 Temporal Difference Updating Without a Learning Rate Marcus Hutter, Shane Legg

COLT 2007 The Loss Rank Principle for Model Selection Marcus Hutter

ALT 2006 Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence Daniil Ryabko, Marcus Hutter

ALT 2006 General Discounting Versus Average Reward Marcus Hutter

IJCAI 2005 A Universal Measure of Intelligence for Artificial Agents Shane Legg, Marcus Hutter

JMLR 2005 Adaptive Online Prediction by Following the Perturbed Leader Marcus Hutter, Jan Poland

ALT 2005 Defensive Universal Learning with Experts Jan Poland, Marcus Hutter

AISTATS 2005 Fast Non-Parametric Bayesian Inference on Infinite Trees Marcus Hutter

ALT 2005 Monotone Conditional Complexity Bounds on Future Prediction Errors Alexey V. Chernov, Marcus Hutter

COLT 2004 Convergence of Discrete MDL for Sequential Prediction Jan Poland, Marcus Hutter

ALT 2004 On the Convergence Speed of MDL Predictions for Bernoulli Sequences Jan Poland, Marcus Hutter

ALT 2004 Prediction with Expert Advice by Following the Perturbed Leader for General Weights Marcus Hutter, Jan Poland

ALT 2004 Universal Convergence of Semimeasures on Individual Random Sequences Marcus Hutter, Andrej Muchnik

COLT 2003 An Open Problem Regarding the Convergence of Universal a Priori Probability Marcus Hutter

ALT 2003 On the Existence and Convergence of Computable Universal Priors Marcus Hutter

JMLR 2003 Optimality of Universal Bayesian Sequence Prediction for General Loss and Alphabet Marcus Hutter

COLT 2003 Sequence Prediction Based on Monotone Complexity Marcus Hutter

UAI 2002 Robust Feature Selection by Mutual Information Distributions Marco Zaffalon, Marcus Hutter

COLT 2002 Self-Optimizing and Pareto-Optimal Policies in General Environments Based on Bayes-Mixtures Marcus Hutter

ECML-PKDD 2001 Convergence and Error Bounds for Universal Prediction of Nonbinary Sequences Marcus Hutter

NeurIPS 2001 Distribution of Mutual Information Marcus Hutter

ICML 2001 General Loss Bounds for Universal Sequence Prediction Marcus Hutter

ECML-PKDD 2001 Towards a Universal Theory of Artificial Intelligence Based on Algorithmic Probability and Sequential Decisions Marcus Hutter