Universal artificial intelligence. Sequential decisions based on algorithmic probability.
DOI10.1007/B138233zbMATH Open1099.68082OpenAlexW2013391942WikidataQ58012464 ScholiaQ58012464MaRDI QIDQ1762575FDOQ1762575
Publication date: 11 February 2005
Published in: Texts in Theoretical Computer Science. An EATCS Series (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/b138233
Recommendations
- Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory
- Reinforcement learning. An introduction
- Asymptotic non-learnability of universal agents with computable horizon functions
- Decision making under uncertainty and reinforcement learning. Theory and algorithms
- Open problems in universal induction \& intelligence
supervised learningstrategic gamessequence predictionsequential decision theoryalgorithmic information theoryfunction minimizationunknown environmentreinforcement learning agent
Learning and adaptive systems in artificial intelligence (68T05) Introductory exposition (textbooks, tutorial papers, etc.) pertaining to computer science (68-01) Algorithmic information theory (Kolmogorov complexity, etc.) (68Q30) General topics in artificial intelligence (68T01)
Cited In (34)
- Simplicity bias, algorithmic probability, and the random logistic map
- Universal knowledge-seeking agents
- On Universal Transfer Learning
- A philosophical treatise of universal induction
- The probability of ``undefined (non-converging) output in generating the universal probability distribution
- The Quest for Uncertainty
- Application of Kolmogorov complexity and universal codes to identity testing and nonparametric testing of serial independence for time series
- Reflective Oracles: A Foundation for Game Theory in Artificial Intelligence
- On the Computability of Solomonoff Induction and Knowledge-Seeking
- Algorithmic complexity bounds on future prediction errors
- Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory
- Time-universal data compression
- Predicting non-stationary processes
- A complete theory of everything (will be subjective)
- Open problems in universal induction \& intelligence
- On generalized computable universal priors and their convergence
- Tractability of batch to sequential conversion
- A theory of incremental compression
- DECISION TREES DO NOT GENERALIZE TO NEW VARIATIONS
- Approval-directed agency and the decision theory of Newcomb-like problems
- On semimeasures predicting Martin-Löf random sequences
- Extreme state aggregation beyond Markov decision processes
- Obituary: Ray Solomonoff, founding father of algorithmic information theory
- General time consistent discounting
- The Neuronal Replicator Hypothesis
- On the possibility of learning in reactive environments with arbitrary dependence
- A Criterion for Optimal Predictive Model Selection
- Sequential predictions based on algorithmic complexity
- Stationary algorithmic probability
- Some Sufficient Conditions on an Arbitrary Class of Stochastic Processes for the Existence of a Predictor
- Reward is enough
- Using ideas of Kolmogorov complexity for studying biological texts
- On the computability of Solomonoff induction and AIXI
- A generalized characterization of algorithmic probability
This page was built for publication: Universal artificial intelligence. Sequential decisions based on algorithmic probability.
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1762575)
