Randomness conservation inequalities; information and independence in mathematical theories
Information and Control
The application of algorithmic probability to problems in artificial intelligence
on Advances in Cognitive Science
Stack computers: the new wave
Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Reinforcement learning in Markovian and non-Markovian environments
NIPS-3 Proceedings of the 1990 conference on Advances in neural information processing systems 3
Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
Inductive functional programming using incremental program transformation
Artificial Intelligence
GPS, a program that simulates human thought
Computers & thought
An introduction to Kolmogorov complexity and its applications (2nd ed.)
An introduction to Kolmogorov complexity and its applications (2nd ed.)
Machine Learning - Special issue on inductive transfer
Genetic programming: an introduction: on the automatic evolution of computer programs and its applications
Reinforcement learning with self-modifying policies
Learning to learn
Learning Team Strategies: Soccer Case Studies
Machine Learning
Toward a Model of Intelligence as an Economy of Agents
Machine Learning
A Theory of Program Size Formally Identical to Information Theory
Journal of the ACM (JACM)
Ant algorithms for discrete optimization
Artificial Life
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Machine Learning
A Representation for the Adaptive Generation of Simple Sequential Programs
Proceedings of the 1st International Conference on Genetic Algorithms
Properties of the Bucket Brigade
Proceedings of the 1st International Conference on Genetic Algorithms
Evolving Structured Programs with Hierarchical Instructions and Skip Nodes
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Extending Planning Graphs to an ADL Subset
ECP '97 Proceedings of the 4th European Conference on Planning: Recent Advances in AI Planning
Self-Optimizing and Pareto-Optimal Policies in General Environments Based on Bayes-Mixtures
COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions
COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
An Ant Colony System Hybridized with a New Local Search for the Sequential Ordering Problem
INFORMS Journal on Computing
Algorithmic Theories of Everything
Algorithmic Theories of Everything
The New AI: General & Sound & Relevant for Physics
The New AI: General & Sound & Relevant for Physics
Simple Principles of Metalearning
Simple Principles of Metalearning
Advances in evolutionary computing
Learning and problem-solving with multilayer connectionist systems (adaptive, strategy learning, neural networks, reinforcement learning)
Theory of Self-Reproducing Automata
Theory of Self-Reproducing Automata
Probabilistic incremental program evolution
Evolutionary Computation
Reinforcement learning: a survey
Journal of Artificial Intelligence Research
Introduction to the Special Issue on Meta-Learning
Machine Learning
Ordered incremental training for GA-based classifiers
Pattern Recognition Letters
Tagging and Referrals in the EVM Architecture
IAT '06 Proceedings of the IEEE/WIC/ACM international conference on Intelligent Agent Technology
Inductive Synthesis of Functional Programs: An Explanation Based Generalization Approach
The Journal of Machine Learning Research
A Working Hypothesis for General Intelligence
Proceedings of the 2007 conference on Advances in Artificial General Intelligence: Concepts, Architectures and Algorithms: Proceedings of the AGI Workshop 2006
A computational approximation to the AIXI model
Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference
Anticipatory Behavior in Adaptive Learning Systems
DS'07 Proceedings of the 10th international conference on Discovery science
Completely self-referential optimal reinforcement learners
ICANN'05 Proceedings of the 15th international conference on Artificial neural networks: formal models and their applications - Volume Part II
A Monte-Carlo AIXI approximation
Journal of Artificial Intelligence Research
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
Towards heuristic algorithmic memory
AGI'11 Proceedings of the 4th international conference on Artificial general intelligence
On the foundations of universal sequence prediction
TAMC'06 Proceedings of the Third international conference on Theory and Applications of Models of Computation
An architecture for self-organising evolvable virtual machines
Engineering Self-Organising Systems
Self-adaptation and dynamic environment experiments with evolvable virtual machines
ESOA'05 Proceedings of the Third international conference on Engineering Self-Organising Systems
2013 Special Issue: First experiments with PowerPlay
Neural Networks
Learning with configurable operators and RL-based heuristics
NFMCP'12 Proceedings of the First international conference on New Frontiers in Mining Complex Patterns
Towards a programming paradigm for control systems with high levels of existential autonomy
AGI'13 Proceedings of the 6th international conference on Artificial General Intelligence
Hi-index | 0.00 |
We introduce a general and in a certain sense time-optimal way of solving one problem after another, efficiently searching the space of programs that compute solution candidates, including those programs that organize and manage and adapt and reuse earlier acquired knowledge. The Optimal Ordered Problem Solver (OOPS) draws inspiration from Levin's Universal Search designed for single problems and universal Turing machines. It spends part of the total search time for a new problem on testing programs that exploit previous solution-computing programs in computable ways. If the new problem can be solved faster by copy-editing/invoking previous code than by solving the new problem from scratch, then OOPS will find this out. If not, then at least the previous solutions will not cause much harm. We introduce an efficient, recursive, backtracking-based way of implementing OOPS on realistic computers with limited storage. Experiments illustrate how OOPS can greatly profit from metalearning or metasearching, that is, searching for faster search procedures.