Stochastic Optimal Control: Theory and Application

By Robert F. Stengel. 1986

How researchers see this paper

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

In Reinforcement Learning

Citations in the corpus

Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-control (2016, methodology): “KL control (Todorov, 2007; Kappen et al., 2012; Rawlik et al., 2012) is a branch of stochastic optimal control (SOC) (Stengel, 1986), which studies an RL, or control, problem in which the agent tries maximizing its task reward while minimizing deviation from a prior policy.”
Reinforcement Learning: A Survey (1996, background): “Adaptive control (Burghes & Graham, 1980; Stengel, 1986) is also concerned with algorithms for improving a sequence of decisions from experience.”
Sample-based informationl-theoretic stochastic optimal control (2014, background): “I. INTRODUCTION In stochastic optimal control (SOC), see [1], [2], [3], [4], we want to compute the optimal control policy for a finite horizon of time steps.”
Variance-constrained filtering for uncertain stochastic systems with missing measurements (2003, methodology): “For instance, the theory of weighted least-squares estimation minimizes a weighted scalar sum of the error variances of the state estimation, but minimizing a scalar sum does not ensure that the multiple variance requirements will be satisfied [23].”
A simple learning strategy for high-speed quadrocopter multi-flips (2010, methodology): “If the system were linear, a time optimal control strategy for the quadrocopter would consist of control actions that lie on the edge of the control envelope [12].”
Adjoint formulation and constraint handling for gradient-based optimization of compositional reservoir flow (2014, background): “Procedures of this type entail the application of optimal control theory and have their roots in the calculus of variations [6, 34].”
Locally Weighted Learning for Control (1997, background): “…long term cost starting from state xd + x turns out to be xT P x. Note that u is a linear function of the state x in Equation 17: u = K x (19) Linear quadratic regulation has useful robustness when compared to deadbeat controllers even if the underlying linear models are imprecise (Stengel 1986).”