Marcus Hutter

Orcid: 0000-0002-3263-4097

Affiliations:
  • DeepMind, UK
  • Australian National University, Canberra, Australia (former)


According to our database1, Marcus Hutter authored at least 243 papers between 2000 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
Evaluating Frontier Models for Dangerous Capabilities.
CoRR, 2024

Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models.
CoRR, 2024

Learning Universal Predictors.
CoRR, 2024

Dynamic Knowledge Injection for AIXI Agents.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Distributional Bellman Operators over Mean Embeddings.
CoRR, 2023

Bridging Algorithmic Information Theory and Machine Learning: A New Approach to Kernel Learning.
CoRR, 2023

Language Modeling Is Compression.
CoRR, 2023

Line Search for Convex Minimization.
CoRR, 2023

Combining a Meta-Policy and Monte-Carlo Planning for Scalable Type-Based Reasoning in Partially Observable Environments.
CoRR, 2023

U-Clip: On-Average Unbiased Stochastic Gradient Clipping.
CoRR, 2023

Self-Predictive Universal AI.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Levin Tree Search with Context Models.
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023

Memory-Based Meta-Learning on Non-Stationary Distributions.
Proceedings of the International Conference on Machine Learning, 2023

Atari-5: Distilling the Arcade Learning Environment down to Five Games.
Proceedings of the International Conference on Machine Learning, 2023

Evaluating Representations with Readout Model Switching.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Neural Networks and the Chomsky Hierarchy.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Sequential Learning of Neural Networks for Prequential MDL.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Universal Agent Mixtures and the Geometry of Intelligence.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022
Fully General Online Imitation Learning.
J. Mach. Learn. Res., 2022

Generalization Bounds for Transfer Learning with Pretrained Classifiers.
CoRR, 2022

Testing Independence of Exchangeable Random Variables.
CoRR, 2022

Beyond Bayes-optimality: meta-learning what you know you don't know.
CoRR, 2022

Formal Algorithms for Transformers.
CoRR, 2022

Neural Networks and the Chomsky Hierarchy.
CoRR, 2022

Uniqueness and Complexity of Inverse MDP Models.
CoRR, 2022

Advanced Artificial Agents Intervene in the Provision of Reward.
AI Mag., 2022

On the Role of Neural Collapse in Transfer Learning.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Reinforcement Learning with Information-Theoretic Actuation.
Proceedings of the Artificial General Intelligence - 15th International Conference, 2022

2021
Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective.
Synth., 2021

Intelligence and Unambitiousness Using Algorithmic Information Theory.
IEEE J. Sel. Areas Inf. Theory, 2021

Curiosity Killed or Incapacitated the Cat and the Asymptotically Optimal Agent.
IEEE J. Sel. Areas Inf. Theory, 2021

Feature Reinforcement Learning: Part II. Structured MDPs.
J. Artif. Gen. Intell., 2021

Isotuning With Applications To Scale-Free Online Learning.
CoRR, 2021

Reducing Planning Complexity of General Reinforcement Learning with Non-Markovian Abstractions.
CoRR, 2021

Shaking the foundations: delusions in sequence models for interaction and control.
CoRR, 2021

Learning Curve Theory.
CoRR, 2021

Counterfactual Credit Assignment in Model-Free Reinforcement Learning.
Proceedings of the 38th International Conference on Machine Learning, 2021

How Useful are Hand-crafted Data? Making Cases for Anomaly Detection Methods.
Proceedings of the 54th Hawaii International Conference on System Sciences, 2021

Reward-Punishment Symmetric Universal Intelligence.
Proceedings of the Artificial General Intelligence - 14th International Conference, 2021

Gated Linear Networks.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Exact Reduction of Huge Action Spaces in General Reinforcement Learning.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Counterfactual Credit Assignment in Model-Free Reinforcement Learning.
CoRR, 2020

On Representing (Anti)Symmetric Functions.
CoRR, 2020

Curiosity Killed the Cat and the Asymptotically Optimal Agent.
CoRR, 2020

A Gentle Introduction to Quantum Computing Algorithms with Applications to Universal Prediction.
CoRR, 2020

A Combinatorial Perspective on Transfer Learning.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Online Learning in Contextual Bandits using Gated Linear Networks.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Logarithmic Pruning is All You Need.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Pessimism About Unknown Unknowns Inspires Conservatism.
Proceedings of the Conference on Learning Theory, 2020

Asymptotically Unambitious Artificial General Intelligence.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
Gated Linear Networks.
CoRR, 2019

Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective.
CoRR, 2019

Fairness without Regret.
CoRR, 2019

Strong Asymptotic Optimality in General Environments.
CoRR, 2019

Conditions on Features for Temporal Difference-Like Methods to Converge.
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019

A Strongly Asymptotically Optimal Agent in General Environments.
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019

Performance Guarantees for Homomorphisms beyond Markov Decision Processes.
Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

2018
On the computability of Solomonoff induction and AIXI.
Theor. Comput. Sci., 2018

Tractability of batch to sequential conversion.
Theor. Comput. Sci., 2018

Convergence of Binarized Context-tree Weighting for Estimating Distributions of Stationary Sources.
Proceedings of the 2018 IEEE International Symposium on Information Theory, 2018

On Q-learning Convergence for Non-Markov Decision Processes.
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018

AGI Safety Literature Review.
Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018

Universal Compression of Piecewise i.i.d. Sources.
Proceedings of the 2018 Data Compression Conference, 2018

2017
Universal Learning Theory.
Proceedings of the Encyclopedia of Machine Learning and Data Mining, 2017

Generalised Discount Functions applied to a Monte-Carlo AImu Implementation.
CoRR, 2017

Reinforcement Learning with a Corrupted Reward Channel.
CoRR, 2017

Count-Based Exploration in Feature Space for Reinforcement Learning.
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

On Thompson Sampling and Asymptotic Optimality.
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

Universal Reinforcement Learning Algorithms: Survey and Experiments.
Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017

Generalised Discount Functions applied to a Monte-Carlo AI u Implementation.
Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems, 2017

A Game-Theoretic Analysis of the Off-Switch Game.
Proceedings of the Artificial General Intelligence - 10th International Conference, 2017

2016
Extreme state aggregation beyond Markov decision processes.
Theor. Comput. Sci., 2016

Thompson Sampling is Asymptotically Optimal in General Environments.
Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence, 2016

Discriminative Hierarchical Rank Pooling for Activity Recognition.
Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016

Loss Bounds and Time Complexity for Speed Priors.
Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, 2016

Death and Suicide in Universal Artificial Intelligence.
Proceedings of the Artificial General Intelligence - 9th International Conference, 2016

Avoiding Wireheading with Value Reinforcement Learning.
Proceedings of the Artificial General Intelligence - 9th International Conference, 2016

Self-Modification of Policy and Utility Function in Rational Agents.
Proceedings of the Artificial General Intelligence - 9th International Conference, 2016

2015
On Martin-Löf (non-)convergence of Solomonoff's universal mixture.
Theor. Comput. Sci., 2015

Rationality, optimism and guarantees in general reinforcement learning.
J. Mach. Learn. Res., 2015

A Topological Approach to Meta-heuristics: Analytical Results on the BFS vs. DFS Algorithm Selection Problem.
CoRR, 2015

On the Computability of AIXI.
Proceedings of the Thirty-First Conference on Uncertainty in Artificial Intelligence, 2015

Online Learning of k-CNF Boolean Functions.
Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, 2015

Bad Universal Priors and Notions of Optimality.
Proceedings of The 28th Conference on Learning Theory, 2015

Analytical Results on the BFS vs. DFS Algorithm Selection Problem: Part II: Graph Search.
Proceedings of the AI 2015: Advances in Artificial Intelligence, 2015

Analytical Results on the BFS vs. DFS Algorithm Selection Problem. Part I: Tree Search.
Proceedings of the AI 2015: Advances in Artificial Intelligence, 2015

On the Computability of Solomonoff Induction and Knowledge-Seeking.
Proceedings of the Algorithmic Learning Theory - 26th International Conference, 2015

Solomonoff Induction Violates Nicod's Criterion.
Proceedings of the Algorithmic Learning Theory - 26th International Conference, 2015

Sequential Extensions of Causal and Evidential Decision Theory.
Proceedings of the Algorithmic Decision Theory - 4th International Conference, 2015

Using Localization and Factorization to Reduce the Complexity of Reinforcement Learning.
Proceedings of the Artificial General Intelligence, 2015

Compress and Control.
Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015

2014
Near-optimal PAC bounds for discounted MDPs.
Theor. Comput. Sci., 2014

General time consistent discounting.
Theor. Comput. Sci., 2014

Online Learning of k-CNF Boolean Functions.
CoRR, 2014

Asymptotics of Continuous Bayes for Non-i.i.d. Sources.
CoRR, 2014

Can we measure the difficulty of an optimization problem?
Proceedings of the 2014 IEEE Information Theory Workshop, 2014

Reflective Features Detection and Hierarchical Reflections Separation in Image Sequences.
Proceedings of the 2014 International Conference on Digital Image Computing: Techniques and Applications, 2014

A Dual Process Theory of Optimistic Cognition.
Proceedings of the 36th Annual Meeting of the Cognitive Science Society, 2014

Free Lunch for optimisation under the universal distribution.
Proceedings of the IEEE Congress on Evolutionary Computation, 2014

Indefinitely Oscillating Martingales.
Proceedings of the Algorithmic Learning Theory - 25th International Conference, 2014

Bayesian Reinforcement Learning with Exploration.
Proceedings of the Algorithmic Learning Theory - 25th International Conference, 2014

Offline to Online Conversion.
Proceedings of the Algorithmic Learning Theory - 25th International Conference, 2014

Extreme State Aggregation beyond MDPs.
Proceedings of the Algorithmic Learning Theory - 25th International Conference, 2014

Intelligence as Inference or Forcing Occam on the World.
Proceedings of the Artificial General Intelligence - 7th International Conference, 2014

Reinforcement learning with value advice.
Proceedings of the Sixth Asian Conference on Machine Learning, 2014

Reliable Point Correspondences in Scenes Dominated by Highly Reflective and Largely Homogeneous Surfaces.
Proceedings of the Computer Vision - ACCV 2014 Workshops, 2014

2013
Guest Editors' foreword.
Theor. Comput. Sci., 2013

Probabilities on Sentences in an Expressive Logic.
J. Appl. Log., 2013

Reinforcement Learning (Dagstuhl Seminar 13321).
Dagstuhl Reports, 2013

On Martin-Löf Convergence of Solomonoff's Mixture.
Proceedings of the Theory and Applications of Models of Computation, 2013

The Sample-Complexity of General Reinforcement Learning.
Proceedings of the 30th International Conference on Machine Learning, 2013

Sparse Adaptive Dirichlet-Multinomial-like Processes.
Proceedings of the COLT 2013, 2013

Universal Knowledge-Seeking Agents for Stochastic Environments.
Proceedings of the Algorithmic Learning Theory - 24th International Conference, 2013

Concentration and Confidence for Discrete Bayesian Sequence Predictors.
Proceedings of the Algorithmic Learning Theory - 24th International Conference, 2013

Learning Agents with Evolving Hypothesis Classes.
Proceedings of the Artificial General Intelligence - 6th International Conference, 2013

Q-learning for history-based reinforcement learning.
Proceedings of the Asian Conference on Machine Learning, 2013

2012
Sparse Sequential Dirichlet Coding
CoRR, 2012

Can Intelligence Explode?
CoRR, 2012

One Decade of Universal Artificial Intelligence
CoRR, 2012

Feature Reinforcement Learning using Looping Suffix Trees.
Proceedings of the Tenth European Workshop on Reinforcement Learning, 2012

Context Tree Switching.
Proceedings of the 2012 Data Compression Conference, Snowbird, UT, USA, April 10-12, 2012, 2012

Adaptive Context Tree Weighting.
Proceedings of the 2012 Data Compression Conference, Snowbird, UT, USA, April 10-12, 2012, 2012

Coding of Non-Stationary Sources as a Foundation for Detecting Change Points and Outliers in Binary Time-Series.
Proceedings of the Tenth Australasian Data Mining Conference, AusDM 2012, Sydney, 2012

Optimistic Agents Are Asymptotically Optimal.
Proceedings of the AI 2012: Advances in Artificial Intelligence, 2012

PAC Bounds for Discounted MDPs.
Proceedings of the Algorithmic Learning Theory - 23rd International Conference, 2012

On Ensemble Techniques for AIXI Approximation.
Proceedings of the Artificial General Intelligence - 5th International Conference, 2012

Optimistic AIXI.
Proceedings of the Artificial General Intelligence - 5th International Conference, 2012

A Noise Tolerant Watershed Transformation with Viscous Force for Seeded Image Segmentation.
Proceedings of the Computer Vision - ACCV 2012, 2012

Context Tree Maximizing.
Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence, 2012

2011
A Monte-Carlo AIXI Approximation.
J. Artif. Intell. Res., 2011

A Philosophical Treatise of Universal Induction.
Entropy, 2011

Algorithmic Randomness as Foundation of Inductive Reasoning and Artificial Intelligence
CoRR, 2011

Universal Learning Theory
CoRR, 2011

Feature Reinforcement Learning in Practice.
Proceedings of the Recent Advances in Reinforcement Learning - 9th European Workshop, 2011

3D Model Assisted Image Segmentation.
Proceedings of the 2011 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2011

A Novel Illumination-Invariant Loss for Monocular 3D Pose Estimation.
Proceedings of the 2011 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2011

(Non-)Equivalence of Universal Priors.
Proceedings of the Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence, 2011

Principles of Solomonoff Induction and AIXI.
Proceedings of the Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence, 2011

No Free Lunch versus Occam's Razor in Supervised Learning.
Proceedings of the Algorithmic Probability and Friends. Bayesian Prediction and Artificial Intelligence, 2011

Axioms for Rational Reinforcement Learning.
Proceedings of the Algorithmic Learning Theory - 22nd International Conference, 2011

Universal Prediction of Selected Bits.
Proceedings of the Algorithmic Learning Theory - 22nd International Conference, 2011

Time Consistent Discounting.
Proceedings of the Algorithmic Learning Theory - 22nd International Conference, 2011

Asymptotically Optimal Agents.
Proceedings of the Algorithmic Learning Theory - 22nd International Conference, 2011

2010
Universal Learning Theory.
Proceedings of the Encyclopedia of Machine Learning, 2010

Model selection with the Loss Rank Principle.
Comput. Stat. Data Anal., 2010

Featureless 2D-3D Pose Estimation by Minimising an Illumination-Invariant Loss
CoRR, 2010

A Bayesian Review of the Poisson-Dirichlet Process
CoRR, 2010

An integrated Bayesian analysis of LOH and copy number data.
BMC Bioinform., 2010

A Complete Theory of Everything (Will Be Subjective).
Algorithms, 2010

Report on the Third Conference on Artificial General Intelligence.
AI Mag., 2010

Consistency of Feature Markov Processes.
Proceedings of the Algorithmic Learning Theory, 21st International Conference, 2010

Editors' Introduction.
Proceedings of the Algorithmic Learning Theory, 21st International Conference, 2010

Reinforcement Learning via AIXI Approximation.
Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence, 2010

2009
Preface.
Theor. Comput. Sci., 2009

Feature Reinforcement Learning: Part I. Unstructured MDPs.
J. Artif. Gen. Intell., 2009

Limits of learning about a categorical latent variable under prior near-ignorance.
Int. J. Approx. Reason., 2009

Practical robust estimators for the imprecise Dirichlet model.
Int. J. Approx. Reason., 2009

Matching 2-D Ellipses to 3-D Circles with Application to Vehicle Pose Estimation
CoRR, 2009

A Monte Carlo AIXI Approximation
CoRR, 2009

Exact Non-Parametric Bayesian Inference on Infinite Trees.
CoRR, 2009

Bayesian DNA copy number analysis.
BMC Bioinform., 2009

Open Problems in Universal Induction & Intelligence.
Algorithms, 2009

A New Local Distance-Based Outlier Detection Approach for Scattered Real-World Data.
Proceedings of the Advances in Knowledge Discovery and Data Mining, 2009

Discrete MDL Predicts in Total Variation.
Proceedings of the Advances in Neural Information Processing Systems 22: 23rd Annual Conference on Neural Information Processing Systems 2009. Proceedings of a meeting held 7-10 December 2009, 2009

Bayesian Joint Estimation of CN and LOH Aberrations.
Proceedings of the Distributed Computing, 2009

2008
On the possibility of learning in reactive environments with arbitrary dependence.
Theor. Comput. Sci., 2008

Algorithmic complexity.
Scholarpedia, 2008

Feature Dynamic Bayesian Networks
CoRR, 2008

Feature Markov Decision Processes
CoRR, 2008

Predictive Hypothesis Identification
CoRR, 2008

Predicting non-stationary processes.
Appl. Math. Lett., 2008

Equivalence of probabilistic tournament and polynomial ranking selection.
Proceedings of the IEEE Congress on Evolutionary Computation, 2008

2007
Universal Algorithmic Intelligence: A Mathematical Top→Down Approach.
Proceedings of the Artificial General Intelligence, 2007

On semimeasures predicting Martin-Löf random sequences.
Theor. Comput. Sci., 2007

On universal prediction and Bayesian confirmation.
Theor. Comput. Sci., 2007

Algorithmic probability.
Scholarpedia, 2007

Algorithmic information theory.
Scholarpedia, 2007

Universal Intelligence: A Definition of Machine Intelligence.
Minds Mach., 2007

Algorithmic complexity bounds on future prediction errors.
Inf. Comput., 2007

Algorithmic Information Theory: a brief non-technical guide to the field
CoRR, 2007

Universal Algorithmic Intelligence: A mathematical top->down approach
CoRR, 2007

On Semimeasures Predicting Martin-Loef Random Sequences
CoRR, 2007

Temporal Difference Updating without a Learning Rate.
Proceedings of the Advances in Neural Information Processing Systems 20, 2007

On Sequence Prediction for Arbitrary Measures.
Proceedings of the IEEE International Symposium on Information Theory, 2007

The Loss Rank Principle for Model Selection.
Proceedings of the Learning Theory, 20th Annual Conference on Learning Theory, 2007

Editors' Introduction.
Proceedings of the Algorithmic Learning Theory, 18th International Conference, 2007

2006
Fitness uniform optimization.
IEEE Trans. Evol. Comput., 2006

On generalized computable universal priors and their convergence.
Theor. Comput. Sci., 2006

MDL convergence speed for Bernoulli sequences.
Stat. Comput., 2006

Sequential predictions based on algorithmic complexity.
J. Comput. Syst. Sci., 2006

Hybrid rounding techniques for knapsack problems.
Discret. Appl. Math., 2006

Bayesian Regression of Piecewise Constant Functions
CoRR, 2006

A Formal Measure of Machine Intelligence
CoRR, 2006

On the Foundations of Universal Sequence Prediction.
Proceedings of the Theory and Applications of Models of Computation, 2006

Metric State Space Reinforcement Learning for a Vision-Capable Mobile Robot.
Proceedings of the Intelligent Autonomous Systems 9, 2006

Learning in Reactive Environments with Arbitrary Dependence.
Proceedings of the Kolmogorov Complexity and Applications, 29.01. - 03.02.2006, 2006

Sequence prediction for non-stationary processes.
Proceedings of the Combinatorial and Algorithmic Foundations of Pattern and Association Discovery, 14.05., 2006

06051 Abstracts Collection -- Kolmogorov Complexity and Applications.
Proceedings of the Kolmogorov Complexity and Applications, 29.01. - 03.02.2006, 2006

Complexity Monotone in Conditions and Future Prediction Errors.
Proceedings of the Kolmogorov Complexity and Applications, 29.01. - 03.02.2006, 2006

Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence.
Proceedings of the Algorithmic Learning Theory, 17th International Conference, 2006

General Discounting Versus Average Reward.
Proceedings of the Algorithmic Learning Theory, 17th International Conference, 2006

Tests of Machine Intelligence.
Proceedings of the 50 Years of Artificial Intelligence, 2006

A Collection of Definitions of Intelligence.
Proceedings of the Advances in Artificial General Intelligence: Concepts, Architectures and Algorithms, 2006

2005
Universal Artificial Intellegence - Sequential Decisions Based on Algorithmic Probability
Texts in Theoretical Computer Science. An EATCS Series, Springer, ISBN: 978-3-540-26877-2, 2005

Asymptotics of discrete MDL for online prediction.
IEEE Trans. Inf. Theory, 2005

Adaptive Online Prediction by Following the Perturbed Leader.
J. Mach. Learn. Res., 2005

Distribution of mutual information from complete and incomplete data.
Comput. Stat. Data Anal., 2005

Strong Asymptotic Assertions for Discrete MDL in Regression and Classification
CoRR, 2005

Universal Learning of Repeated Matrix Games
CoRR, 2005

Master Algorithms for Active Experts Problems based on Increasing Loss Values
CoRR, 2005

Robust inference of trees.
Ann. Math. Artif. Intell., 2005

A Universal Measure of Intelligence for Artificial Agents.
Proceedings of the IJCAI-05, Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence, Edinburgh, Scotland, UK, July 30, 2005

Fitness uniform deletion: a simple way to preserve diversity.
Proceedings of the Genetic and Evolutionary Computation Conference, 2005

Defensive Universal Learning with Experts.
Proceedings of the Algorithmic Learning Theory, 16th International Conference, 2005

Monotone Conditional Complexity Bounds on Future Prediction Errors.
Proceedings of the Algorithmic Learning Theory, 16th International Conference, 2005

Fast Non-Parametric Bayesian Inference on Infinite Trees.
Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, 2005

2004
Convergence of Discrete MDL for Sequential Prediction.
Proceedings of the Learning Theory, 17th Annual Conference on Learning Theory, 2004

Tournament versus fitness uniform selection.
Proceedings of the IEEE Congress on Evolutionary Computation, 2004

On the Convergence Speed of MDL Predictions for Bernoulli Sequences.
Proceedings of the Algorithmic Learning Theory, 15th International Conference, 2004

Prediction with Expert Advice by Following the Perturbed Leader for General Weights.
Proceedings of the Algorithmic Learning Theory, 15th International Conference, 2004

Universal Convergence of Semimeasures on Individual Random Sequences.
Proceedings of the Algorithmic Learning Theory, 15th International Conference, 2004

2003
Convergence and loss bounds for Bayesian sequence prediction.
IEEE Trans. Inf. Theory, 2003

Optimality of Universal Bayesian Sequence Prediction for General Loss and Alphabet.
J. Mach. Learn. Res., 2003

Optimal Sequential Decisions based on Algorithmic Probability
CoRR, 2003

Bayesian Treatment of Incomplete Discrete Data Applied to Mutual Information and Feature Selection.
Proceedings of the KI 2003: Advances in Artificial Intelligence, 2003

Robust Estimators under the Imprecise Dirichlet Model.
Proceedings of the ISIPTA '03, 2003

An Open Problem Regarding the Convergence of Universal A Priori Probability.
Proceedings of the Computational Learning Theory and Kernel Machines, 2003

Sequence Prediction Based on Monotone Complexity.
Proceedings of the Computational Learning Theory and Kernel Machines, 2003

On the Existence and Convergence of Computable Universal Priors.
Proceedings of the Algorithmic Learning Theory, 14th International Conference, 2003

2002
The Fastest and Shortest Algorithm for all Well-Defined Problems.
Int. J. Found. Comput. Sci., 2002

Robust Feature Selection by Mutual Information Distributions.
Proceedings of the UAI '02, 2002

Self-Optimizing and Pareto-Optimal Policies in General Environments Based on Bayes-Mixtures.
Proceedings of the Computational Learning Theory, 2002

Fitness uniform selection to preserve genetic diversity.
Proceedings of the 2002 Congress on Evolutionary Computation, 2002

2001
New Error Bounds for Solomonoff Prediction.
J. Comput. Syst. Sci., 2001

An effective Procedure for Speeding up Algorithms
CoRR, 2001

Gradient-based Reinforcement Planning in Policy-Search Methods
CoRR, 2001

Distribution of Mutual Information.
Proceedings of the Advances in Neural Information Processing Systems 14 [Neural Information Processing Systems: Natural and Synthetic, 2001

General Loss Bounds for Universal Sequence Prediction.
Proceedings of the Eighteenth International Conference on Machine Learning (ICML 2001), Williams College, Williamstown, MA, USA, June 28, 2001

Market-Based Reinforcement Learning in Partially Observable Worlds.
Proceedings of the Artificial Neural Networks, 2001

Convergence and Error Bounds for Universal Prediction of Nonbinary Sequences.
Proceedings of the Machine Learning: EMCL 2001, 2001

Towards a Universal Theory of Artificial Intelligence Based on Algorithmic Probability and Sequential Decisions.
Proceedings of the Machine Learning: EMCL 2001, 2001

2000
Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory
CoRR, 2000

A Theory of Universal Artificial Intelligence based on Algorithmic Complexity
CoRR, 2000


  Loading...