Marcus Hutter

RL, but don’t do anything I wouldn’t do UAI 2025 Distributional Bellman Operators over Mean Embeddings ICML 2024 Dynamic Knowledge Injection for AIXI Agents AAAI 2024 Language Modeling Is Compression ICLR 2024 Learning Universal Predictors ICML 2024 Atari-5: Distilling the Arcade Learning Environment down to Five Games ICML 2023 Evaluating Representations with Readout Model Switching ICLR 2023 Levin Tree Search with Context Models IJCAI 2023 Memory-Based Meta-Learning on Non-Stationary Distributions ICML 2023 Neural Networks and the Chomsky Hierarchy ICLR 2023 Self-Predictive Universal AI NeurIPS 2023 Sequential Learning of Neural Networks for Prequential MDL ICLR 2023 Universal Agent Mixtures and the Geometry of Intelligence AISTATS 2023 Fully General Online Imitation Learning JMLR 2022 On the Role of Neural Collapse in Transfer Learning ICLR 2022 Counterfactual Credit Assignment in Model-Free Reinforcement Learning ICML 2021 Exact Reduction of Huge Action Spaces in General Reinforcement Learning AAAI 2021 Gated Linear Networks AAAI 2021 A Combinatorial Perspective on Transfer Learning NeurIPS 2020 Asymptotically Unambitious Artificial General Intelligence AAAI 2020 Logarithmic Pruning is All You Need NeurIPS 2020 Online Learning in Contextual Bandits using Gated Linear Networks NeurIPS 2020 Pessimism About Unknown Unknowns Inspires Conservatism COLT 2020 A Strongly Asymptotically Optimal Agent in General Environments IJCAI 2019 Conditions on Features for Temporal Difference-Like Methods to Converge IJCAI 2019 Performance Guarantees for Homomorphisms beyond Markov Decision Processes AAAI 2019 AGI Safety Literature Review IJCAI 2018 On Q-learning Convergence for Non-Markov Decision Processes IJCAI 2018 Count-Based Exploration in Feature Space for Reinforcement Learning IJCAI 2017 On Thompson Sampling and Asymptotic Optimality IJCAI 2017 Universal Reinforcement Learning Algorithms: Survey and Experiments IJCAI 2017 Discriminative Hierarchical Rank Pooling for Activity Recognition CVPR 2016 Loss Bounds and Time Complexity for Speed Priors AISTATS 2016 Bad Universal Priors and Notions of Optimality COLT 2015 Online Learning of k-CNF Boolean Functions IJCAI 2015 Rationality, Optimism and Guarantees in General Reinforcement Learning JMLR 2015 Reinforcement learning with value advice ACML 2014 Q-learning for history-based reinforcement learning ACML 2013 Sparse Adaptive Dirichlet-Multinomial-like Processes COLT 2013 The Sample-Complexity of General Reinforcement Learning ICML 2013 Discrete MDL Predicts in Total Variation NeurIPS 2009 Temporal Difference Updating without a Learning Rate NeurIPS 2007 Adaptive Online Prediction by Following the Perturbed Leader JMLR 2005 Optimality of Universal Bayesian Sequence Prediction for General Loss and Alphabet JMLR 2003