Learning dynamical systems in a stationary environment

DOI10.1016/S0167-6911(98)00005-XzbMath0909.93082MaRDI QIDQ1274409

P. R. Kumar, Marco C. Campi

Publication date: 12 January 1999

Published in: Systems \& Control Letters (Search for Journal in Brave)

zbMATH Keywords

PACdynamical systemslearningstationarityprobably approximately correct

Mathematics Subject Classification ID

Identification in stochastic control theory (93E12) Stochastic learning and adaptive control (93E35) General systems theory (93A99)

Related Items

Learning with side information: PAC learning bounds, Finite sample properties of system identification of ARX models under mixing conditions, Bayesian system identification via Markov chain Monte Carlo techniques, Plug and play robust distributed control with ellipsoidal parametric uncertainty system, Estimation and approximation bounds for gradient-based reinforcement learning, Application of interval predictor model into robust model predictive control

Cites Work

• Unnamed Item
• Unnamed Item
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Exploiting random walks for learning
• A Markovian extension of Valiant's learning model
• Probably Approximate Learning of Sets and Functions
• A theory of the learnable
• Necessary and Sufficient Conditions for the Uniform Convergence of Means to their Expectations
• Probably Approximate Learning over Classes of Distributions
• Learning by canonical smooth estimation. I. Simultaneous estimation
• Learning by canonical smooth estimation. II. Learning and choice of model complexity
• The central limit problem for mixing sequences of random variables
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Convergence of stochastic processes