Stochastic Optimal Control and Estimation Methods Adapted to the Noise Characteristics of the Sensorimotor System

By E. Todorov. Neural Computation, 2005

414 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Generalized Path Integral Control Approach to Reinforcement Learning (2010, methodology): “There are very few optimal control algorithms which compute all three issues simultaneously, such as Differential Dynamic Programming(DDP) (Jacobson and Mayne, 1970), or its simpler version the Iterative Linear Quadratic Regulator(iLQR) (Todorov, 2005).”
A computational neuroanatomy for motor control (2008, background): “combination of Gaussian noise stochastic variables / i 'N0;1 "# with zero mean and variance one ( Todorov 2005 ):”
Geometrical Invariance and Smoothness Maximization for Task-Space Movement Generation (2016, background): “Other studies have examined the nature of the noise associated with human movement, investigating different sources of noise either separately or in combination [11], [35], [52].”
Evidence for the Flexible Sensorimotor Strategies Predicted by Optimal Feedback Control (2007, background): “Thepresenceofsignal-dependentnoisecomplicatesmatters;however, wederivedanefficientalgorithmforsolvingsuchproblemspreviously (Todorov,2005).”
A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems (2005, methodology): “However, we have recently solved such a problem for linear systems [16], and are now working on adapting that methodology to the ILQG framework.”
Motor Adaptation as a Process of Reoptimization (2008, positive): “Recent advances in optimal control theory (Todorov, 2005)”