Partially observable nonlinear risk-sensitive control problems: dynamic programming and verification theorems

In this paper, we consider continuous-time partially observable optimal control problems with exponential-of-integral cost criteria. We derive a rigorous verification theorem when the state and control enter nonlinear in the dynamics. In addition, we show that the quadratic sensor problem is estimation-solvable with respect to a certain cost criterion. The framework relies on dynamic programming and the Hamilton-Jacobi theory.

[1]  C. Charalambous,et al.  Minimum principle for partially observable nonlinear risk-sensitive control problems using measure-valued decompositions , 1996 .

[2]  A. Bensoussan,et al.  Optimal control of partially observable stochastic systems with an exponential-of-integral performance index , 1985 .

[3]  W. Wonham.  On the Separation Theorem of Stochastic Control , 1968 .

[4]  P. Whittle.  A risk-sensitive maximum principle: the case of imperfect state observation , 1991 .

[5]  Andrzej Świe,et al.  Risk-sensitive Control and Diierential Games in Innnite Dimensions 1 , 2022 .

[6]  Kevin L. Moore,et al.  Solvable risk-sensitive control problems with output feedback , 1994, Proceedings of 1994 33rd IEEE Conference on Decision and Control.

[7]  V. Benes.  Exact finite-dimensional filters for certain diffusions with nonlinear drift , 1981 .

[8]  Alʹbert Nikolaevich Shiri︠a︡ev,et al.  Statistics of random processes , 1977 .

[9]  J. H. van Schuppen,et al.  On the optimal control of stochastic systems with an exponential-of-integral performance index , 1981 .

[10]  Matthew R. James,et al.  Asymptotic analysis of nonlinear stochastic risk-sensitive control and differential games , 1992, Math. Control. Signals Syst..

[11]  Robert J. Elliott,et al.  A Finite-Dimensional Risk-Sensitive Control Problem , 1995 .

[12]  A. Bensoussan.  Stochastic Control of Partially Observable Systems , 1992 .

[13]  L. Shepp,et al.  Wiener Integrals Associated with Diffusion Processes , 1968 .

[14]  K. Glover,et al.  State-space formulae for all stabilizing controllers that satisfy and H ∞ norm bound and relations to risk sensitivity , 1988 .

[15]  P. Whittle.  Risk-Sensitive Optimal Control , 1990 .

[16]  P. Whittle.  Risk-sensitive linear/quadratic/gaussian control , 1981, Advances in Applied Probability.

[17]  M. James,et al.  Risk-sensitive control and dynamic games for partially observed discrete-time nonlinear systems , 1994, IEEE Trans. Autom. Control..

[18]  C. Charalambous.  The role of information state and adjoint in relating nonlinear output feedback risk-sensitive control and dynamic games , 1997, IEEE Trans. Autom. Control..

[19]  Etienne Pardoux,et al.  A conditionally almost Linear filtering problem with non-Gaussian initial condition , 1988 .

[20]  Jason Speyer.  An adaptive terminal guidance scheme based on an exponential cost criterion with application to homing missile guidance , 1975, 1975 IEEE Conference on Decision and Control including the 14th Symposium on Adaptive Processes.

[21]  S.,et al.  Risk-Sensitive Control and Dynamic Games for Partially Observed Discrete-Time Nonlinear Systems , 1994 .

[22]  Robert J. Elliott,et al.  General finite-dimensional risk-sensitive problems and small noise limits , 1996, IEEE Trans. Autom. Control..

[23]  W. Fleming,et al.  Risk sensitive optimal control and differential games , 1992 .

[24]  Rhodes,et al.  Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic differential games , 1973 .