English
Related papers

Related papers: A Robust Model-Based Approach for Continuous-Time …

200 papers

Oftentimes, environments for sequential decision-making problems can be quite sparse in the provision of evaluative feedback to guide reinforcement-learning agents. In the extreme case, long trajectories of behavior are merely punctuated…

Machine Learning · Computer Science 2023-08-22 Akash Velu , Skanda Vaidyanath , Dilip Arumugam

Model-based reinforcement learning algorithms tend to achieve higher sample efficiency than model-free methods. However, due to the inevitable errors of learned models, model-based methods struggle to achieve the same asymptotic performance…

Machine Learning · Computer Science 2019-12-02 Qi Zhou , Houqiang Li , Jie Wang

This paper investigates a class of stochastic Logistic harvesting models driven by tempered stable processes, with a one-sided power-law L\'evy measure. We establish threshold conditions for population extinction and persistence, prove the…

Optimization and Control · Mathematics 2026-05-18 Wenmin Deng , Fu Zhang

We study the problem of system identification for stochastic continuous-time dynamics, based on a single finite-length state trajectory. We present a method for estimating the possibly unstable open-loop matrix by employing properly…

Machine Learning · Statistics 2025-09-30 Reza Sadeghi Hafshejani , Mohamad Kazem Shirani Fradonbeh

Trust is the invisible glue that holds together the fabric of societies, economic systems, and political institutions. Yet, its dynamics-especially in real-world settings remain unpredictable and difficult to control. While classical trust…

Applications · Statistics 2026-01-05 Mohamadali Berahman , Madjid Eshaghi Gordji

Multi-stage decision-making under uncertainty, where decisions are taken under sequentially revealing uncertain problem parameters, is often essential to faithfully model managerial problems. Given the significant computational challenges…

Optimization and Control · Mathematics 2026-04-30 Simon Thomä , Maximilian Schiffer , Wolfram Wiesemann

In model-free deep reinforcement learning (RL) algorithms, using noisy value estimates to supervise policy evaluation and optimization is detrimental to the sample efficiency. As this noise is heteroscedastic, its effects can be mitigated…

Machine Learning · Computer Science 2022-05-04 Vincent Mai , Kaustubh Mani , Liam Paull

We are motivated by the real challenges presented in a human-robot system to develop new designs that are efficient at data level and with performance guarantees such as stability and optimality at systems level. Existing…

Systems and Control · Electrical Eng. & Systems 2021-01-19 Xiang Gao , Jennie Si , Yue Wen , Minhan Li , He , Huang

Causal inference from observational datasets often relies on measuring and adjusting for covariates. In practice, measurements of the covariates can often be noisy and/or biased, or only measurements of their proxies may be available.…

Machine Learning · Computer Science 2022-02-23 Wenshuo Guo , Mingzhang Yin , Yixin Wang , Michael I. Jordan

With the rapid increase of valuable observational, experimental and simulated data for complex systems, much efforts have been devoted to identifying governing laws underlying the evolution of these systems. Despite the wide applications of…

Machine Learning · Statistics 2021-10-01 Yang Li , Yubin Lu , Shengyuan Xu , Jinqiao Duan

In reinforcement learning, temporal abstraction in the action space, exemplified by action repetition, is a technique to facilitate policy learning through extended actions. However, a primary limitation in previous studies of action…

Machine Learning · Computer Science 2024-02-09 Joongkyu Lee , Seung Joon Park , Yunhao Tang , Min-hwan Oh

This paper introduces a learning-based, data-driven attitude estimator, called the retrospective cost attitude estimator (RCAE), for the SO(3) attitude representation. RCAE is motivated by the multiplicative extended Kalman filter (MEKF).…

Optimization and Control · Mathematics 2025-01-15 Parham Oveissi , Mohammad Mirtaba , Ankit Goel

Sparse Identification of Nonlinear Dynamics (SINDy) is a method of system discovery that has been shown to successfully recover governing dynamical systems from data (Brunton et al., PNAS, '16; Rudy et al., Sci. Adv. '17). Recently, several…

Numerical Analysis · Mathematics 2021-07-28 Daniel A. Messenger , David M. Bortz

We consider the problem of system identification of partially observed linear time-invariant (LTI) systems. Given input-output data, we provide non-asymptotic guarantees for identifying the system parameters under general heavy-tailed noise…

Systems and Control · Electrical Eng. & Systems 2025-04-28 Vinay Kanakeri , Aritra Mitra

Off-policy learning and evaluation leverage logged bandit feedback datasets, which contain context, action, propensity score, and feedback for each data point. These scenarios face significant challenges due to high variance and poor…

Machine Learning · Computer Science 2025-06-10 Armin Behnamnia , Gholamali Aminian , Alireza Aghaei , Chengchun Shi , Vincent Y. F. Tan , Hamid R. Rabiee

We present a data-driven approach for producing policies that are provably robust across unknown stochastic environments. Existing approaches can learn models of a single environment as an interval Markov decision processes (IMDP) and…

Machine Learning · Computer Science 2025-03-25 Yannik Schnitzer , Alessandro Abate , David Parker

Continuous-time nonlinear optimal control problems hold great promise in real-world applications. After decades of development, reinforcement learning (RL) has achieved some of the greatest successes as a general nonlinear control design…

Systems and Control · Electrical Eng. & Systems 2023-07-19 Brent A. Wallace , Jennie Si

Reliable predictions of critical phenomena, such as weather, wildfires and epidemics often rely on models described by Partial Differential Equations (PDEs). However, simulations that capture the full range of spatio-temporal scales…

Machine Learning · Computer Science 2025-02-13 Jan-Philipp von Bassewitz , Sebastian Kaltenbach , Petros Koumoutsakos

Discrete-time linear time-varying (LTV) systems form a powerful class of models to approximate complex dynamical systems with nonlinear dynamics for the purpose of analysis, design and control. Motivated by inference of spatio-temporal…

Systems and Control · Computer Science 2018-05-23 Roel Dobbe , Stephan Liu , Ye Yuan , Claire Tomlin

Identifying unknown differential equations from a given set of discrete time dependent data is a challenging problem. A small amount of noise can make the recovery unstable, and nonlinearity and differential equations with varying…

Numerical Analysis · Mathematics 2019-04-09 Sung Ha Kang , Wenjing Liao , Yingjie Liu