Shifting Inductive Bias with Success-Story Algorithm, Adaptive Levin Search, and Incremental Self-Improvement

Keywords

Inductive bias, Computer science, Reinforcement learning, Backtracking, Undo

References

• Theory Formation by Heuristic SearchDouglas B. Lenat — 1983
• Book Review: An introduction to Kolmogorov Complexity and its Applications Second Edition, 1997 by Ming Li and Paul Vitanyi (Springer (Graduate Text Series))William Gasarch — 1997
• A Representation for the Adaptive Generation of Simple Sequential ProgramsNichael Lynn Cramer — 1985
• Solving POMDPs with Levin Search and EIRAMarco Wiering, Jürgen Schmidhuber — 1996
• Stochastic Systems: Estimation, Identification, and Adaptive ControlP. R. Kumar, Pravin Varaiya — 1986
• Genetic evolution and co-evolution of computer programsJohn R. Koza — 1991
• Reinforcement Learning for Robots Using Neural NetworksLong-Ji Lin — 1992
• Shift of bias for inductive concept learningPaul E. Utgoff — 1984
• An Introduction to Kolmogorov Complexity and Its ApplicationsMing Li, Paul Vitányi — 1993
• Reinforcement Learning with Perceptual Aliasing: The Perceptual Distinctions ApproachLonnie Chrisman — 1992
• Learning in embedded systemsLeslie Pack Kaelbling — 1993
• Adding Temporary Memory to ZCSDave Cliff, Susi Ross — 1994
• Three approaches to the quantitative definition of informationA. N. Kolmogorov — 1968
• Deliberation Scheduling for Problem Solving in Time-Constrained EnvironmentsMark Boddy, Thomas Dean — 1994
• PALO: A Probabilistic Hill-Climbing AlgorithmRussell Greiner — 1996
• Randomness Conservation Inequalities; Information and Independence in Mathematical TheoriesLeonid A. Levin — 1984
• Active Perception and Reinforcement LearningSteven D. Whitehead, Dana H. Ballard — 1990
• Learning Automata - A SurveyKumpati S. Narendra, M.A.L. Thathachar — 1974
• Bandit Problems, Sequential Allocation of ExperimentsPeter W. Jones — 1987
• A Survey of Transfer Between Connectionist NetworksLorien Pratt, Barbara Jennings — 1996

Cited by

• Using Markov-k Memory for Problems with Hidden-StateMatthew W. Mitchell — 2003
• Bias-Optimal Incremental Learning of Control Sequences for Virtual RobotsJuergen Schmidhuber, Viktor Zhumatiy, Matteo Gagliolo — 2004
• Intrinsically Motivated Learning in Natural and Artificial SystemsGianluca Baldassarre — 2013
• Cumulative learning in the lambda calculusRobert Henderson — 2013
• Self-Delimiting Neural NetworksJuergen Schmidhuber — 2012
• Reinforcement learning algorithms for solving classification problemsMarco Wiering, Hado van Hasselt, Auke-Dirk Pietersma — 2011
• Learning Team Strategies: Soccer Case StudiesRafał Sałustowicz, Marco Wiering, Jürgen Schmidhuber — 1998
• From Seed AI to Technological Singularity via Recursively Self-Improving SoftwareRoman V. Yampolskiy — 2015
• Reinforcement Learning by Policy SearchLeslie Pack Kaelbling, Leonid Peshkin — 2002
• Computers and CreativityJon McCormack, d’Inverno, Mark — 2012
• Teraflop-scale Incremental Machine LearningEray Özkural — 2011
• Abstraction Super-Structuring Normal Forms: Towards a Theory of Structural InductionAdrian Silvescu, Vasant Honavar — 2011
• Artificial motivations based on drive-reduction theory in self-referential model-building control systemsMoritz Schneider, Jürgen Adamy — 2015
• The automatic generation of mutation operators for genetic algorithmsJohn R. Woodward, Jerry Swan — 2012
• Genetic programming using adaptable stochastic flow of controlArtur Rataj — 2010
• Optimal Ordered Problem SolverJürgen Schmidhuber — 2002
• Formal Theory of Creativity, Fun, and Intrinsic Motivation (1990–2010)Jürgen Schmidhuber — 2010
• Learning dynamic algorithm portfoliosMatteo Gagliolo, Jürgen Schmidhuber — 2006
• First Experiments with PowerPlayRupesh K. Srivastava, Bas R. Steunebrink, Jürgen Schmidhuber — 2012
• Learning parallel portfolios of algorithmsMarek Petrik, Shlomo Zilberstein — 2006

Related papers

• Selective backtracking of model changesIris Groher, Alexander Egyed — 2009
• A demonstration of AZURITE: Backtracking tool for programmersYoungSeok Yoon, Brad A. Myers — 2014
• Multitask Learning Over Graphs: An Approach for Distributed, Streaming Machine LearningRoula Nassif, Stefan Vlaski, Cédric Richard — 2020
• A Model of Inductive Bias LearningJonathan Baxter — 2000
• Adjusting Bias in Concept LearningPaul E. Utgoff — 1983
• Policies for the selection of bias in inductive machine learningJohn Foster Provost — 1992
• Incorporating prior domain knowledge into inductive machine learning : its implementation in contemporary capital marketsTing Yu — 2007
• Local Nonparametric Meta-LearningWonjoon Goo, Scott Niekum — 2020