English
Related papers

Related papers: Reinforcement Learning, Optimal Control, and Bayes…

200 papers

Practical data assimilation algorithms often contain hyper-parameters, which may arise due to, for instance, the use of certain auxiliary techniques like covariance inflation and localization in an ensemble Kalman filter, the…

Computation · Statistics 2022-06-08 Xiaodong Luo , Chuan-An Xia

We analyze the Bayesian regret of the Gaussian process posterior sampling reinforcement learning (GP-PSRL) algorithm. Posterior sampling is an effective heuristic for decision-making under uncertainty that has been used to develop…

Machine Learning · Statistics 2026-03-10 Hamish Flynn , Joe Watson , Ingmar Posner , Jan Peters

Dropout, a stochastic regularisation technique for training of neural networks, has recently been reinterpreted as a specific type of approximate inference algorithm for Bayesian neural networks. The main contribution of the…

Machine Learning · Statistics 2018-07-06 Jiri Hron , Alexander G. de G. Matthews , Zoubin Ghahramani

We present a new algorithm based on posterior sampling for learning in Constrained Markov Decision Processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous…

Machine Learning · Computer Science 2024-05-30 Danil Provodin , Maurits Kaptein , Mykola Pechenizkiy

This paper provides a detailed theoretical analysis of methods to approximate the solutions of high-dimensional (>10^6) linear Bayesian problems. An optimal low-rank projection that maximizes the information content of the Bayesian…

Data Analysis, Statistics and Probability · Physics 2019-10-28 Nicolas Bousserez , Daven K. Henze

A common problem in Machine Learning and statistics consists in detecting whether the current sample in a stream of data belongs to the same distribution as previous ones, is an isolated outlier or inaugurates a new distribution of data. We…

Machine Learning · Statistics 2018-05-16 Vincent Moens

This study presents a Bayesian learning perspective towards model predictive control algorithms. High-level frameworks have been developed separately in the earlier studies on Bayesian learning and sampling-based model predictive control.…

Machine Learning · Computer Science 2022-03-14 Namhoon Cho , Seokwon Lee , Hyo-Sang Shin , Antonios Tsourdos

We propose the use of Bayesian networks, which provide both a mean value and an uncertainty estimate as output, to enhance the safety of learned control policies under circumstances in which a test-time input differs significantly from the…

Machine Learning · Computer Science 2019-02-18 Keuntaek Lee , Kamil Saigol , Evangelos A. Theodorou

A framework for data assimilation combining aspects of operator-theoretic ergodic theory and quantum mechanics is developed. This framework adapts the Dirac--von Neumann formalism of quantum dynamics and measurement to perform sequential…

Mathematical Physics · Physics 2019-09-18 Dimitrios Giannakis

We present new policy mirror descent (PMD) methods for solving reinforcement learning (RL) problems with either strongly convex or general convex regularizers. By exploring the structural properties of these overall highly nonconvex…

Machine Learning · Computer Science 2022-04-08 Guanghui Lan

Controlled interacting particle systems such as the ensemble Kalman filter (EnKF) and the feedback particle filter (FPF) are numerical algorithms to approximate the solution of the nonlinear filtering problem in continuous time. The…

Systems and Control · Electrical Eng. & Systems 2019-10-08 Amirhossein Taghvaei , Prashant G. Mehta

State-action value functions (i.e., Q-values) are ubiquitous in reinforcement learning (RL), giving rise to popular algorithms such as SARSA and Q-learning. We propose a new notion of action value defined by a Gaussian smoothed version of…

Machine Learning · Computer Science 2018-07-26 Ofir Nachum , Mohammad Norouzi , George Tucker , Dale Schuurmans

We develop an algebraic framework for sequential data assimilation of partially observed dynamical systems. In this framework, Bayesian data assimilation is embedded in a non-abelian operator algebra, which provides a representation of…

Statistics Theory · Mathematics 2023-03-29 David Freeman , Dimitrios Giannakis , Brian Mintz , Abbas Ourmazd , Joanna Slawinska

In this work, we aim at studying ensemble based optimal control strategies for data assimilation. Such formulation nicely combines the ingredients of ensemble Kalman filters and variational data assimilation (4DVar). In the same way as…

Mathematical Physics · Physics 2014-01-17 Yin Yang , Cordelia Robinson , Dominique Heitz , Etienne Mémin

This work highlights the duality between state estimation methods and model predictive control. A predictive controller, observed control, is presented that uses this duality to efficiently compute control actions with linear time-horizon…

Optimization and Control · Mathematics 2025-08-20 Eugene T. Hamzezadeh , Andrew J. Petruska

Data-driven prediction and physics-agnostic machine-learning methods have attracted increased interest in recent years achieving forecast horizons going well beyond those to be expected for chaotic dynamical systems. In a separate strand of…

Data Analysis, Statistics and Probability · Physics 2021-05-19 Georg A. Gottwald , Sebastian Reich

We explore reinforcement learning methods for finding the optimal policy in the linear quadratic regulator (LQR) problem. In particular, we consider the convergence of policy gradient methods in the setting of known and unknown parameters.…

Machine Learning · Computer Science 2021-06-25 Ben Hambly , Renyuan Xu , Huining Yang

Existing score-based methods for inverse problems often resort to approximate minimization of the KL divergence between the inversion distribution and the Bayesian posterior. Such an approximation leads to severe mode collapse and…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Weimin Bai , Yuxuan Gu , Yifei Wang , Weijian Luo , He Sun

Data assimilation schemes are confronted with the presence of model errors arising from the imperfect description of atmospheric dynamics. These errors are usually modeled on the basis of simple assumptions such as bias, white noise, first…

Chaotic Dynamics · Physics 2009-11-13 A. Carrassi , S. Vannitsem , C. Nicolis

The connection between control algorithms for Markov decision processes and optimization algorithms has been implicitly and explicitly exploited since the introduction of dynamic programming algorithm by Bellman in the 1950s. Recently, this…

Optimization and Control · Mathematics 2025-12-09 Tolga Ok , Arman Sharifi Kolarijani , Mohamad Amin Sharif Kolarijani , Peyman Mohajerin Esfahani