English
Related papers

Related papers: Understanding the Effect of Stochasticity in Polic…

200 papers

Stochastic optimization problems often involve data distributions that change in reaction to the decision variables. This is the case for example when members of the population respond to a deployed classifier by manipulating their features…

Optimization and Control · Mathematics 2020-12-15 Dmitriy Drusvyatskiy , Lin Xiao

Motivated by emerging applications in machine learning, we consider an optimization problem in a general form where the gradient of the objective function is available through a biased stochastic oracle. We assume a bias-control parameter…

Optimization and Control · Mathematics 2026-02-10 Yin Liu , Sam Davanloo Tajbakhsh

The intersection of causal inference and machine learning for decision-making is rapidly expanding, but the default decision criterion remains an \textit{average} of individual causal outcomes across a population. In practice, various…

Machine Learning · Computer Science 2022-11-08 Wenshuo Guo , Michael I. Jordan , Angela Zhou

In order to compute near-optimal policies with policy-gradient algorithms, it is common in practice to include intrinsic exploration terms in the learning objective. Although the effectiveness of these terms is usually justified by an…

Machine Learning · Computer Science 2025-08-21 Adrien Bolland , Gaspard Lambrechts , Damien Ernst

In performative prediction, the choice of a model influences the distribution of future data, typically through actions taken based on the model's predictions. We initiate the study of stochastic optimization for performative prediction.…

Machine Learning · Computer Science 2021-02-22 Celestine Mendler-Dünner , Juan C. Perdomo , Tijana Zrnic , Moritz Hardt

We study contextual stochastic optimization problems, where we leverage rich auxiliary observations (e.g., product characteristics) to improve decision making with uncertain variables (e.g., demand). We show how to train forest decision…

Optimization and Control · Mathematics 2022-03-17 Nathan Kallus , Xiaojie Mao

Policy gradient (PG) methods are successful approaches to deal with continuous reinforcement learning (RL) problems. They learn stochastic parametric (hyper)policies by either exploring in the space of actions or in the space of parameters.…

Machine Learning · Computer Science 2024-05-31 Alessandro Montenegro , Marco Mussi , Alberto Maria Metelli , Matteo Papini

The goal of policy gradient approaches is to find a policy in a given class of policies which maximizes the expected return. Given a differentiable model of the policy, we want to apply a gradient-ascent technique to reach a local optimum.…

Machine Learning · Computer Science 2019-11-13 Mattis Manfred Kämmerer

Policy optimization algorithms are crucial in many fields but challenging to grasp and implement, often due to complex calculations related to Markov decision processes and varying use of discount and average reward setups. This paper…

Systems and Control · Electrical Eng. & Systems 2025-04-07 Shuang Wu

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

Machine Learning · Computer Science 2020-10-16 Alekh Agarwal , Sham M. Kakade , Jason D. Lee , Gaurav Mahajan

We analyze convergence rates of stochastic optimization procedures for non-smooth convex optimization problems. By combining randomized smoothing techniques with accelerated gradient methods, we obtain convergence rates of stochastic…

Optimization and Control · Mathematics 2012-04-10 John C. Duchi , Peter L. Bartlett , Martin J. Wainwright

Off-policy stochastic actor-critic methods rely on approximating the stochastic policy gradient in order to derive an optimal policy. One may also derive the optimal policy by approximating the action-value gradient. The use of action-value…

Machine Learning · Statistics 2017-03-14 Yemi Okesanjo , Victor Kofia

This paper concerns discrete-time infinite-horizon stochastic control systems with Borel state and action spaces and universally measurable policies. We study optimization problems on strategic measures induced by the policies in these…

Optimization and Control · Mathematics 2023-12-22 Huizhen Yu

When looking for a solution, deterministic methods have the enormous advantage that they do find global optima. Unfortunately, they are very CPU-intensive, and are useless on untractable NP-hard problems that would require thousands of…

Neural and Evolutionary Computing · Computer Science 2011-12-20 Pierre Collet , Jean-Philippe Rennard

Distribution shifts have long been regarded as troublesome external forces that a decision-maker should either counteract or conform to. An intriguing feedback phenomenon termed decision dependence arises when the deployed decision affects…

Optimization and Control · Mathematics 2025-03-11 Zhiyu He , Saverio Bolognani , Florian Dörfler , Michael Muehlebach

It is well known that for any finite state Markov decision process (MDP) there is a memoryless deterministic policy that maximizes the expected reward. For partially observable Markov decision processes (POMDPs), optimal memoryless policies…

Optimization and Control · Mathematics 2016-02-16 Guido Montufar , Keyan Ghazi-Zahedi , Nihat Ay

A widely used heuristic for solving stochastic optimization problems is to use a deterministic rolling horizon procedure, which has been modified to handle uncertainty (e.g. buffer stocks, schedule slack). This approach has been criticized…

Optimization and Control · Mathematics 2017-03-16 Raymond T. Perkins , Warren B. Powell

Batch policy optimization considers leveraging existing data for policy construction before interacting with an environment. Although interest in this problem has grown significantly in recent years, its theoretical foundations remain…

Machine Learning · Computer Science 2021-04-07 Chenjun Xiao , Yifan Wu , Tor Lattimore , Bo Dai , Jincheng Mei , Lihong Li , Csaba Szepesvari , Dale Schuurmans

We consider the problem of finding the best memoryless stochastic policy for an infinite-horizon partially observable Markov decision process (POMDP) with finite state and action spaces with respect to either the discounted or mean reward…

Optimization and Control · Mathematics 2022-05-02 Johannes Müller , Guido Montúfar

We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying MDPs controlled by the underlying…

Optimization and Control · Mathematics 2024-08-27 Sihan Zeng , Thinh T. Doan , Justin Romberg
‹ Prev 1 2 3 10 Next ›