English
Related papers

Related papers: Optimistic Value Iteration

200 papers

A hidden Markov process is a well known concept in information theory and is used for a vast range of applications such as speech recognition and error correction. We bridge between two disciplines, experimental physics and advanced…

Mesoscale and Nanoscale Physics · Physics 2015-06-24 Ido Kanter , Aviad Frydman , Asaf Ater

Practical model building processes are often time-consuming because many different models must be trained and validated. In this paper, we introduce a novel algorithm that can be used for computing the lower and the upper bounds of model…

Machine Learning · Statistics 2014-02-11 Yoshiki Suzuki , Kohei Ogawa , Yuki Shinmura , Ichiro Takeuchi

Iterative preference optimization methods have recently been shown to perform well for general instruction tuning tasks, but typically make little improvement on reasoning tasks (Yuan et al., 2024, Chen et al., 2024). In this work we…

Computation and Language · Computer Science 2024-06-27 Richard Yuanzhe Pang , Weizhe Yuan , Kyunghyun Cho , He He , Sainbayar Sukhbaatar , Jason Weston

An important step in the Markov reward approach to error bounds on stationary performance measures of Markov chains is to bound the bias terms. Affine functions have been successfully used for these bounds for various models, but there are…

Probability · Mathematics 2019-01-04 Xinwei Bai , Jasper Goseling

Stochastic optimization is a vital field in the realm of mathematical optimization, finding applications in diverse areas ranging from operations research to machine learning. In this paper, we introduce a novel first-order optimization…

Optimization and Control · Mathematics 2024-09-17 Vladimir Solodkin , Savelii Chezhegov , Ruslan Nazikov , Aleksandr Beznosikov , Alexander Gasnikov

We propose a novel iterative algorithm for estimating a deterministic but unknown parameter vector in the presence of model uncertainties. This iterative algorithm is based on a system model where an overall noise term describes both, the…

Statistics Theory · Mathematics 2017-11-27 Oliver Lang , Michael Lunglmayr , Mario Huemer

We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics. In this setting, we propose a new performance metric, planning regret, which replaces the standard…

Machine Learning · Computer Science 2021-03-01 Naman Agarwal , Elad Hazan , Anirudha Majumdar , Karan Singh

In this paper, we consider the gradual-impulse control problem of continuous-time Markov decision processes, where the system performance is measured by the expectation of the exponential utility of the total cost. We prove, under very…

Optimization and Control · Mathematics 2023-11-16 Xin Guo , Aiko Kurushima , Alexey Piunovskiy , Yi Zhang

We consider Markov decision processes (MDPs) with multiple limit-average (or mean-payoff) objectives. There exist two different views: (i) the expectation semantics, where the goal is to optimize the expected mean-payoff objective, and (ii)…

Logic in Computer Science · Computer Science 2019-03-14 Krishnendu Chatterjee , Zuzana Křetínská , Jan Křetínský

This paper addresses the problem of optimal control of robotic sensing systems aimed at autonomous information gathering in scenarios such as environmental monitoring, search and rescue, and surveillance and reconnaissance. The information…

Systems and Control · Computer Science 2016-01-28 Mikko Lauri , Nikolay Atanasov , George J. Pappas , Risto Ritala

Stochastic min-max optimization has gained interest in the machine learning community with the advancements in GANs and adversarial training. Although game optimization is fairly well understood in the deterministic setting, some issues…

Machine Learning · Computer Science 2024-03-27 Juan Ramirez , Rohan Sukumaran , Quentin Bertrand , Gauthier Gidel

We analyze a simple randomized subgradient method for approximating solutions to stochastic systems of convex functional constraints, the only input to the algorithm being the size of minibatches. By introducing a new notion of what is…

Optimization and Control · Mathematics 2021-08-30 James Renegar , Song Zhou

We propose a Bayesian optimization algorithm for objective functions that are sums or integrals of expensive-to-evaluate functions, allowing noisy evaluations. These objective functions arise in multi-task Bayesian optimization for tuning…

Machine Learning · Computer Science 2018-03-26 Saul Toscano-Palmerin , Peter I. Frazier

We study a localized notion of uniform convergence known as an "optimistic rate" (Panchenko 2002; Srebro et al. 2010) for linear regression with Gaussian data. Our refined analysis avoids the hidden constant and logarithmic factor in…

Machine Learning · Statistics 2021-12-09 Lijia Zhou , Frederic Koehler , Danica J. Sutherland , Nathan Srebro

Inference for partially observed Markov process models has been a longstanding methodological challenge with many scientific and engineering applications. Iterated filtering algorithms maximize the likelihood function for partially observed…

Statistics Theory · Mathematics 2012-11-26 Edward L. Ionides , Anindya Bhadra , Yves Atchadé , Aaron King

Inverse optimization (IO) seeks to infer the parameters of a decision-maker's objective from observed context--action data. We study noiseless IO, where demonstrations are generated by a ground-truth objective. We provide a high-probability…

Machine Learning · Statistics 2026-05-12 Pouria Fatemi , Hoomaan Maskan , Suvrit Sra , Peyman Mohajerin Esfahani

Autonomous systems are often required to operate in partially observable environments. They must reliably execute a specified objective even with incomplete information about the state of the environment. We propose a methodology to…

Artificial Intelligence · Computer Science 2020-01-14 Maxime Bouton , Jana Tumova , Mykel J. Kochenderfer

Consider the problem of joint parameter estimation and prediction in a Markov random field: i.e., the model parameters are estimated on the basis of an initial set of data, and then the fitted model is used to perform prediction (e.g.,…

Machine Learning · Computer Science 2007-07-13 Martin J. Wainwright

We consider partially observable Markov decision processes (POMDPs) with a set of target states and every transition is associated with an integer cost. The optimization objective we study asks to minimize the expected total cost till the…

Artificial Intelligence · Computer Science 2014-11-17 Krishnendu Chatterjee , Martin Chmelík , Raghav Gupta , Ayush Kanodia

We formulate a probabilistic Markov property in discrete time under a dynamic risk framework with minimal assumptions. This is useful for recursive solutions to risk-sensitive versions of dynamic optimisation problems such as optimal…

Optimization and Control · Mathematics 2022-09-05 Tomasz Kosmala , Randall Martyr , John Moriarty