Nothing Special   »   [go: up one dir, main page]

Huynh et al., 2014 - Google Patents

A martingale approach and time-consistent sampling-based algorithms for risk management in stochastic optimal control

Huynh et al., 2014

View PDF
Document ID
10689417612536467175
Author
Huynh V
Kogan L
Frazzoli E
Publication year
Publication venue
53rd IEEE Conference on Decision and Control

External Links

Snippet

In this paper, we consider a class of stochastic optimal control problems with risk constraints that are expressed as bounded probabilities of failure for particular initial states. We present here a martingale approach that diffuses a risk constraint into a martingale to construct time …
Continue reading at arxiv.org (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/0285—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks and fuzzy logic
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/0275—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using fuzzy logic only

Similar Documents

Publication Publication Date Title
Wachi et al. Safe reinforcement learning in constrained markov decision processes
US10423129B2 (en) Controlling dynamical systems with bounded probability of failure
Dutta et al. Reachability analysis for neural feedback systems using regressive polynomial rule inference
Wabersich et al. Linear model predictive safety certification for learning-based control
Everitt et al. Reinforcement learning with a corrupted reward channel
Wabersich et al. Safe exploration of nonlinear dynamical systems: A predictive safety filter for reinforcement learning
Golowich et al. Planning in observable pomdps in quasipolynomial time
Bonzanini et al. Safe learning-based model predictive control under state-and input-dependent uncertainty using scenario trees
Chaudhari et al. Sampling-based algorithms for continuous-time POMDPs
Jackson et al. Safety verification of unknown dynamical systems via gaussian process regression
Lorenzen et al. An improved constraint-tightening approach for stochastic MPC
Hakobyan et al. Distributionally robust risk map for learning-based motion planning and control: A semidefinite programming approach
da Silva et al. Active perception and control from temporal logic specifications
Ahmadi et al. Verification of uncertain POMDPs using barrier certificates
Lechner et al. Infinite time horizon safety of bayesian neural networks
von Rohr et al. Probabilistic robust linear quadratic regulators with Gaussian processes
Rafieisakhaei et al. Feedback motion planning under non-gaussian uncertainty and non-convex state constraints
Sadraddini et al. Formal methods for adaptive control of dynamical systems
Shirai et al. Chance-constrained optimization in contact-rich systems for robust manipulation
Huynh et al. A martingale approach and time-consistent sampling-based algorithms for risk management in stochastic optimal control
Bao et al. Learning-based adaptive-scenario-tree model predictive control with probabilistic safety guarantees using bayesian neural networks
Zhai et al. Region of Attraction for Power Systems using Gaussian Process and Converse Lyapunov Function--Part I: Theoretical Framework and Off-line Study
Jeddi et al. Lyapunov-based uncertainty-aware safe reinforcement learning
Wang et al. Reinforcement learning with temporal logic constraints for partially-observable markov decision processes
Min et al. Constructing confidence sets after lasso selection by randomized estimator augmentation