New method solves uncertain control problems with model uncertainty.
problem Solving uncertain stochastic Markovian control problems in discrete time.
method Adaptive robust control approach using Bellman equation and recursive confidence regions.
result Success of the approach demonstrated through optimal portfolio allocation problem.
The paper tackles robust control with uncertain dependence using data-driven methods.
problem Nonparametric robust control under dependence uncertainty in multi-period stochastic systems.
method Nonparametric adaptive robust control framework using stochastic gradient descent ascent algorithm.
result The controller benefits from knowing more about the uncertain model.
A method for accurate pricing of multidimensional derivatives under uncertain volatility.
problem High-dimensional stochastic control problem in uncertain volatility model.
method Backward actor-critic stochastic policy gradient scheme combining DP, PPO, and neural networks.
result Accurate and efficient pricing of multidimensional derivatives compared to benchmarks.
Dual control approximates Bayesian RL for uncertain systems.
problem Bayesian reinforcement learning in uncertain systems is intractable.
method Extended dual control approach using generalized linear regression.
result Structured exploration strategies different from standard RL.
This paper first describes a class of uncertain stochastic control systems with Markovian switching, and derives an Itô-Liu formula for Markov-modulated processes. And we characterize an optimal control law, which satisfies the generalized Hamilton-Jacobi-Bellman (HJB) equation with Markovian switching. Then, by using …
Paper proposes online optimization for uncertain systems using machine learning and DRO.
problem Optimization of uncertain dynamical systems with distributional uncertainty.
method Combines machine learning with Distributional Robust Optimization (DRO) to handle uncertainty.
result Online solutions with probabilistic regret bounds for uncertain systems.
New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.
problem Model-based policy learning in uncertain, time-varying dynamics.
method Planning regret metric and iterative algorithm for minimizing it.
result Empirical evidence shows the proposed algorithm outperforms existing methods.
AntLer anticipates future learning to improve control performance.
problem Improving control performance through online learning is not well understood.
method AntLer uses a probabilistic model to anticipate future learning and optimize control parameters.
result AntLer approximates optimal solutions with high probability.
Safe learning in uncertain systems with state measurements and optimization.
problem Safe learning in nonlinear control-affine systems with unknown additive uncertainty.
method Model uncertainty as Gaussian noise, learn mean and covariance, use optimization to adjust control input.
result Guaranteed safety with arbitrarily large probability while learning and control proceed simultaneously.
Proposes a recursive MPC scheme with probabilistic safety guarantees for uncertain dynamic systems.
problem Probabilistic safety guarantees for MPC in dynamic environments with unknown stochastic agents.
method Uses conformal prediction to derive high-confidence prediction regions and gradually relax safety constraints online.
result Ensures recursive feasibility of MPC schemes by relaxing safety constraints over time.
The paper tackles robust control for insurance contracts under uncertain transition rates.
problem Maximizing utility in insurance contracts with uncertain transition rates.
method Novel robust utility maximization problem under bounded cumulative transition rate uncertainty, using worst-case scenario analysis.
result Existence and uniqueness of worst-case and best-case reserves for insurance contracts.
We study an optimal execution problem with uncertain market impact to derive a more realistic market model. We construct a discrete-time model as a value function for optimal execution. Market impact is formulated as the product of a deterministic part increasing with execution volume and a positive stochastic noise pa…
The paper tackles controlling gene regulatory networks with noisy measurements and uncertain inputs.
problem Controlling gene regulatory networks with indirect measurements and uncertain inputs.
method Modeling GRNs with POBDS, transforming to a Markov Decision Process, using Gaussian processes for cost function, and applying reinforcement learning and sparsification.
result Near-optimal control strategy for infinite-horizon control of GRNs is found.
Bayesian algorithm stabilizes unknown continuous-time systems from unstable data.
problem Learning and stabilizing unknown continuous-time systems with uncertain dynamics.
method Bayesian learning algorithm that learns from unstable data to stabilize the system in finite time.
result The algorithm stabilizes unknown continuous-time stochastic linear systems effectively after a short time period.
A new method solves complex financial equations efficiently.
problem Solving worst-case and best-case prices for two-factor uncertain volatility models.
method Decompose and integrate, then optimize; piecewise constant control; closed-form Green's functions; 2D convolution integrals; monotone numerical integration; Fast Fourier Transforms.
result The method efficiently computes the value function and optimal control, converging to the viscosity solution of the HJB equation.
Framework for robust control in cooperative systems with uncertain common noise.
problem Optimizing collective behavior of agents in the presence of uncertain common noise.
method Proposes a robust mean-field control framework and proves existence of optimal controls.
result Existence of optimal open-loop controls linked to a lifted robust Markov decision problem.
A machine learning method optimizes portfolio and hedging under uncertain market parameters.
problem Optimizing portfolios and hedging under drift and volatility uncertainty.
method Machine learning approach solving adaptive robust control problems.
result Demonstrates financial advantages of adaptive robust framework.
DRO optimizes decisions under uncertain distributions, considering worst-case scenarios.
problem Optimizing decisions when the distribution of uncertainties is itself uncertain.
method Defines ambiguity sets and seeks decisions optimal under the worst-case distribution.
result DRO models can be connected to regularization techniques and machine learning.
uMoE trains NNs with uncertain data by embedding uncertainty into training.
problem Managing aleatoric uncertainty in NN-based predictive models.
method Divide and Conquer strategy, Expert components, Gating Unit.
result uMoE outperforms baseline methods in uncertainty management.
Survey of RL methods for optimizing power grid topologies.
problem Optimizing power grid operation with adaptive control strategies.
method Reinforcement Learning (RL) for dynamic and uncertain environments.
result Comprehensive evaluation of RL-based methods for power grid topology optimization.
Optimizes heating setpoints with uncertain loads using various feedback types.
problem Optimizing heating setpoints with uncertain, flexible loads.
method Online convex optimization (OCO) with different types of feedback.
result Sublinear regret bounds achieved in all feedback types.
Develops a framework for quantifying agentic AI model risk using LLM-inferred Bayesian state filters.
problem Quantifying the risk of agentic AI systems due to uncertain beliefs and actions.
method Representing the system as a partially observed Markov decision process with latent states, Bayesian belief updates, control-dependent losses, and tail-risk functionals.
result Develops a rigorous framework for separating uncertainty quantification from risk measurement.
Intelligent control for greenhouses using deep reinforcement learning.
problem Uncertain nonlinear system of greenhouse environment control.
method Model Embedded Deep Reinforcement Learning (MEDRL) with computer vision and crop growth models.
result Precision and convenience in precise control of greenhouse environment.
We propose a probabilistic numerical algorithm to solve Backward Stochastic Differential Equations (BSDEs) with nonnegative jumps, a class of BSDEs introduced in [9] for representing fully nonlinear HJB equations. In particular, this allows us to numerically solve stochastic control problems with controlled volatility,…
Unified control theory and machine learning for safety in uncertain systems.
problem Safety guarantees for systems with measurement model uncertainty.
method Measurement-Robust Control Barrier Functions (MR-CBFs) for control synthesis.
result MR-CBFs ensure safety in perception systems with measurement model uncertainty.
New LQR kernels improve controller learning from data.
problem Optimal controller design for nonlinear systems from data is challenging.
method Developed LQR kernels for Bayesian optimization.
result LQR kernels lead to superior learning performance on uncertain systems.
This paper extends transfer learning for linear regression to uncertain domain information.
problem Transfer learning for linear regression with uncertain domain information.
method A Dirichlet process is used to infer latent domain information from regression coefficients. A novel framework considers the joint distribution of variables.
result The proposed method controls bias better than previous pseudo-labelling approaches.
Develops a risk-sensitive reinforcement learning framework for uncertain environments.
problem Learning in uncertain environments with varying risk preferences.
method Integrates utility functions and risk measures into reinforcement learning, tuning risk preference with parameter β.
result Risk-averse, risk-neutral, and risk-taking behaviors can be achieved and compared.
Paper optimizes financial trading strategies under uncertain market conditions.
problem Guaranteeing robust positive expected profits in financial systems.
method Transformed semi-infinite constraints into structured policies and proposed a novel graphical approach.
result Demonstrated superior risk-adjusted returns and downside risk compared to conventional strategies.
This work proposes a new method for simultaneous probabilistic identification and control of an observable, fully-actuated mechanical system. Identification is achieved by conditioning stochastic process priors on observations of configurations and noisy estimates of configuration derivatives. In contrast to previous w…
New robust control method for uncertain systems using bootstrapped noise.
problem Designing controllers robust to model uncertainties in finite data.
method Least-squares model estimator, bootstrap resampling, multiplicative noise LQR.
result Significantly outperforms certainty equivalent controllers in numerical tests.
Paper uses ML for high-dimensional option pricing under uncertain volatility model.
problem High-dimensional option pricing under uncertain volatility.
method Two ML approaches: GTU and NNU.
result Significant improvement in option pricing precision.
Paper develops online learning-based risk-averse MPC for uncertain systems.
problem Designing robust MPC for systems with unknown but inferable stochastic disturbances.
method Proposes a novel online learning framework using CVaR constraints and Dirichlet process mixture models.
result Demonstrates improved robustness and adaptability of MPC in handling time-varying disturbance distributions.
Paper values equity warrants using uncertain calculus.
problem Valuing equity warrants in uncertain financial markets.
method Used uncertain calculus to solve equity warrants pricing problem.
result Equation for equity warrants pricing derived for uncertain stock model.
Paper tackles robust control policy learning for uncertain systems.
problem Learning control policies for an unknown linear dynamical system with quadratic cost.
method Convex optimization method balancing exploitation and exploration.
result Minimizes worst-case cost by reducing uncertainty in model parameters.
Optimizes costs in uncertain Markov systems using risk filters.
problem Optimizing costs in systems with model uncertainty and unknown parameters.
method Risk filters and Bellman principle of optimality applied to Bayesian framework.
result Derives the Bellman principle for non-standard risk-averse control problems.
PLoM learns stochastic solutions to PDEs with limited data.
problem Synthesizing solutions to nonlinear PDEs with scarce data.
method Probabilistic Learning on Manifolds constrained by PDEs.
result Learned stochastic solutions minimize PDE residuals.
The paper explores how to handle uncertain evidence in probabilistic models.
problem Handling uncertain evidence in probabilistic models and stochastic simulators.
method The paper considers distributional evidence, Jeffrey's rule, and virtual evidence as methods for interpreting uncertain evidence.
result The paper provides guidelines on how to account for uncertain evidence and highlights the importance of careful consideration.
Deep Autoencoder using GANs detects faults in closed loop systems without labeled data.
problem Fault detection in closed loop uncertain dynamical systems.
method Generative Adversarial Network (GAN) based Autoencoder.
result The proposed method significantly outperforms traditional classifier-based methods.
Survey of reinforcement learning in continuous control, focusing on LQR.
problem Optimizing control in uncertain environments with models and cost of generality.
method Survey and case study of LQR, merging learning theory and control.
result Theoretical and experimental characterizations match, showing the role of models.
New method calculates Shapley values for uncertain functions.
problem Uncertain value functions in explainable machine learning.
method Definition of Shapley values using probability theory.
result Shapley values can be applied to uncertain functions.
Proposes a CVaR-based method to learn robust options in uncertain environments.
problem Learning options from inaccurate models with uncertain parameters.
method Extends CVaR-based policy gradient method to robust Markov decision processes.
result Produces options that perform well in both average and worst cases.
Bayesian method optimizes uncertain constraints in black-box function optimization.
problem Optimizing black-box functions with uncertain environmental variables.
method Distributionally robust chance-constrained Bayesian optimization.
result The method can find accurate solutions with high probability in a finite number of trials.
Investigates timing and asset allocation for life insurance in uncertain financial planning.
problem Optimal timing and asset allocation for life insurance in uncertain financial planning.
method Analytical solutions using duality theory and free-boundary problems.
result Explicit expressions for value functions and optimal strategies in both scenarios.
Research improves fraud detection in e-commerce by predicting delayed transaction data.
problem Accurate fraud detection in e-commerce transactions with delayed labels.
method Developed two frameworks, CEI and FEI, to estimate decision environment features using mature and partially mature data.
result Proposed frameworks significantly improved fraud detection accuracy.
UAIL uses uncertainty estimation to improve control systems in safety-critical tasks.
problem Improving control systems in safety-critical domains like autonomous driving.
method UAIL applies Monte Carlo Dropout to estimate uncertainty in control output and selectively acquire new training data.
result UAIL can reliably predict infractions and outperforms existing algorithms.
A new method for estimating uncertainties in neural ODEs without numerical integration.
problem Accurate estimation of predictive uncertainties in neural ODEs.
method Distributional Gradient Matching (DGM) algorithm that jointly trains a smoother and a dynamics model.
result Significantly more accurate predictions compared to traditional methods.
New model-free reinforcement learning methods outperform traditional scheduling in cancer chemotherapy.
problem Optimal scheduling of cancer chemotherapy in the presence of uncertainty.
method Used Deep Q-Network (DQN) and Deep Deterministic Policy Gradient (DDPG) algorithms.
result DDPG outperforms DQN in eradicating cancer, suggesting continuous action space advantages.