English
Related papers

Related papers: Policy Optimization Through Approximate Importance…

200 papers

Current methods for end-to-end constructive neural combinatorial optimization usually train a policy using behavior cloning from expert solutions or policy gradient methods from reinforcement learning. While behavior cloning is…

Machine Learning · Computer Science 2024-11-05 Jonathan Pirnay , Dominik G. Grimm

We consider the problem of sequential sampling from a finite number of independent statistical populations to maximize the expected infinite horizon average outcome per period, under a constraint that the expected average sampling cost does…

Machine Learning · Statistics 2012-01-20 Apostolos Burnetas , Odysseas Kanavetas

Post-training with reinforcement learning (RL) has recently shown strong promise for advancing multimodal agents beyond supervised imitation. However, RL remains limited by poor data efficiency, particularly in settings where interaction…

Machine Learning · Computer Science 2026-03-05 Chengxuan Lu , Zhenquan Zhang , Shukuan Wang , Qunzhi Lin , Baigui Sun , Yang Liu

We consider the infinite-horizon discounted optimal control problem formalized by Markov Decision Processes. We focus on several approximate variations of the Policy Iteration algorithm: Approximate Policy Iteration, Conservative Policy…

Artificial Intelligence · Computer Science 2014-05-13 Bruno Scherrer

We develop an optimization framework centered around a core idea: once a (parametric) policy is specified, control authority is transferred to the policy, resulting in an autonomous dynamical system. Thus we should be able to optimize…

Machine Learning · Computer Science 2025-06-11 Emo Todorov

We develop an approach to risk minimization and stochastic optimization that provides a convex surrogate for variance, allowing near-optimal and computationally efficient trading between approximation and estimation error. Our approach…

Machine Learning · Statistics 2017-12-15 John Duchi , Hongseok Namkoong

Previous work has shown the unreliability of existing algorithms in the batch Reinforcement Learning setting, and proposed the theoretically-grounded Safe Policy Improvement with Baseline Bootstrapping (SPIBB) fix: reproduce the baseline…

Machine Learning · Computer Science 2021-01-01 Thiago D. Simão , Romain Laroche , Rémi Tachet des Combes

Policy learning utilizing observational data is pivotal across various domains, with the objective of learning the optimal treatment assignment policy while adhering to specific constraints such as fairness, budget, and simplicity. This…

Methodology · Statistics 2023-10-12 Pan Zhao , Antoine Chambaz , Julie Josse , Shu Yang

One popular method for dealing with large-scale data sets is sampling. For example, by using the empirical statistical leverage scores as an importance sampling distribution, the method of algorithmic leveraging samples and rescales…

Methodology · Statistics 2013-06-25 Ping Ma , Michael W. Mahoney , Bin Yu

This work develops new algorithms with rigorous efficiency guarantees for infinite horizon imitation learning (IL) with linear function approximation without restrictive coherence assumptions. We begin with the minimax formulation of the…

Machine Learning · Computer Science 2023-05-31 Luca Viano , Angeliki Kamoutsi , Gergely Neu , Igor Krawczuk , Volkan Cevher

We study sampling problems associated with potentials that lack smoothness. The potentials can be either convex or non-convex. Departing from the standard smooth setting, the potentials are only assumed to be weakly smooth or non-smooth, or…

Machine Learning · Computer Science 2023-07-04 Jiaming Liang , Yongxin Chen

Policy gradient methods are widely adopted reinforcement learning algorithms for tasks with continuous action spaces. These methods succeeded in many application domains, however, because of their notorious sample inefficiency their use…

Machine Learning · Statistics 2024-02-20 Davide Mambelli , Stephan Bongers , Onno Zoeter , Matthijs T. J. Spaan , Frans A. Oliehoek

The Robbins-Monro stochastic approximation algorithm is a foundation of many algorithmic frameworks for reinforcement learning (RL), and often an efficient approach to solving (or approximating the solution to) complex optimal control…

Optimization and Control · Mathematics 2019-03-19 Andrey Bernstein , Yue Chen , Marcello Colombino , Emiliano Dall'Anese , Prashant Mehta , Sean Meyn

In order for reinforcement learning techniques to be useful in real-world decision making processes, they must be able to produce robust performance from limited data. Deep policy optimization methods have achieved impressive results on…

Machine Learning · Computer Science 2020-12-22 James Queeney , Ioannis Ch. Paschalidis , Christos G. Cassandras

Every prediction is ultimately used in a downstream task. Consequently, evaluating prediction quality is more meaningful when considered in the context of its downstream use. Metrics based solely on predictive performance often diverge from…

Machine Learning · Computer Science 2025-08-26 Novin Shahroudi , Viacheslav Komisarenko , Meelis Kull

The policy gradient theorem (Sutton et al., 2000) prescribes the usage of a cumulative discounted state distribution under the target policy to approximate the gradient. Most algorithms based on this theorem, in practice, break this…

Machine Learning · Computer Science 2022-07-08 Samuele Tosatto , Andrew Patterson , Martha White , A. Rupam Mahmood

Learning optimal policies from historical data enables personalization in a wide variety of applications including healthcare, digital recommendations, and online education. The growing policy learning literature focuses on settings where…

Machine Learning · Statistics 2022-11-17 Ruohan Zhan , Zhimei Ren , Susan Athey , Zhengyuan Zhou

Modern stochastic optimization methods often rely on uniform sampling which is agnostic to the underlying characteristics of the data. This might degrade the convergence by yielding estimates that suffer from a high variance. A possible…

Machine Learning · Statistics 2018-06-07 Zalán Borsos , Andreas Krause , Kfir Y. Levy

This note introduces Isometric Policy Optimization (ISOPO), an efficient method to approximate the natural policy gradient in a single gradient step. In comparison, existing proximal policy methods such as GRPO or CISPO use multiple…

Machine Learning · Computer Science 2026-01-01 Nilin Abrahamsen

For obtaining optimal first-order convergence guarantee for stochastic optimization, it is necessary to use a recurrent data sampling algorithm that samples every data point with sufficient frequency. Most commonly used data sampling…

Optimization and Control · Mathematics 2024-07-23 William G. Powell , Hanbaek Lyu
‹ Prev 1 8 9 10 Next ›