English
Related papers

Related papers: Wasserstein Adaptive Value Estimation for Actor-Cr…

200 papers

Distributionally Robust Optimization (DRO) has enabled to prove the equivalence between robustness and regularization in classification and regression, thus providing an analytical reason why regularization generalizes well in statistical…

Optimization and Control · Mathematics 2020-07-15 Esther Derman , Shie Mannor

Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures. However, applying similar methods to discrete structures,…

Machine Learning · Computer Science 2018-07-02 Jake Zhao , Yoon Kim , Kelly Zhang , Alexander M. Rush , Yann LeCun

Algorithmic stability is an important notion that has proven powerful for deriving generalization bounds for practical algorithms. The last decade has witnessed an increasing number of stability bounds for different algorithms applied on…

Machine Learning · Statistics 2023-10-31 Lingjiong Zhu , Mert Gurbuzbalaban , Anant Raj , Umut Simsekli

We propose iterative algorithms to solve adversarial problems in a variety of supervised learning settings of interest. Our algorithms, which can be interpreted as suitable ascent-descent dynamics in Wasserstein spaces, take the form of a…

Machine Learning · Computer Science 2023-01-11 Camilo Garcia Trillos , Nicolas Garcia Trillos

Standard stochastic control methods assume that the probability distribution of uncertain variables is available. Unfortunately, in practice, obtaining accurate distribution information is a challenging task. To resolve this issue, we…

Optimization and Control · Mathematics 2021-10-13 Insoon Yang

Mainstream approximate action-value iteration reinforcement learning (RL) algorithms suffer from overestimation bias, leading to suboptimal policies in high-variance stochastic environments. Quantile-based action-value iteration methods…

Machine Learning · Computer Science 2025-12-09 Clinton Enwerem , Aniruddh G. Puranic , John S. Baras , Calin Belta

Distributionally robust optimization (DRO) has become a powerful framework for estimation under uncertainty, offering strong out-of-sample performance and principled regularization. In this paper, we propose a DRO-based method for linear…

Machine Learning · Statistics 2025-05-06 Liviu Aolaritei , Soroosh Shafiee , Florian Dörfler

Actor-critic algorithms have become a cornerstone in reinforcement learning (RL), leveraging the strengths of both policy-based and value-based methods. Despite recent progress in understanding their statistical efficiency, no existing work…

Machine Learning · Statistics 2025-05-07 Kevin Tan , Wei Fan , Yuting Wei

The Andrew's sine function is a robust estimator, which has been used in outlier rejection and robust statistics. However, the performance of such estimator does not receive attention in the field of adaptive filtering techniques. Two…

Systems and Control · Electrical Eng. & Systems 2023-03-30 Lu Lu , Yi Yu , Zongsheng Zheng , Guangya Zhu , Xiaomin Yang

In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action…

Machine Learning · Computer Science 2018-06-20 Shangda Li , Selina Bing , Steven Yang

We study the global convergence and global optimality of actor-critic, one of the most popular families of reinforcement learning algorithms. While most existing works on actor-critic employ bi-level or two-timescale updates, we focus on…

Machine Learning · Computer Science 2021-06-15 Zuyue Fu , Zhuoran Yang , Zhaoran Wang

We propose using the Wasserstein loss for training in inverse problems. In particular, we consider a learned primal-dual reconstruction scheme for ill-posed inverse problems using the Wasserstein distance as loss function in the learning.…

Computer Vision and Pattern Recognition · Computer Science 2017-10-31 Jonas Adler , Axel Ringh , Ozan Öktem , Johan Karlsson

Reinforcement learning from human feedback (RLHF) has become a core post-training step for aligning large language models, yet the reward signal used in RLHF is only a learned proxy for true human utility. From an operations research…

Machine Learning · Computer Science 2026-05-19 Yikai Wang , Shang Liu , Jose Blanchet

We investigate a dynamic inverse problem using a regularization which implements the so-called Wasserstein-$1$ distance. It naturally extends well-known static problems such as lasso or total variation regularized problems to a (temporally)…

Optimization and Control · Mathematics 2025-12-05 Marcello Carioni , Julius Lohmann

We describe an application of Wasserstein distance to Reinforcement Learning. The Wasserstein distance in question is between the distribution of mappings of trajectories of a policy into some metric space, and some other fixed distribution…

Machine Learning · Computer Science 2019-08-01 Mohammed Amin Abdullah , Aldo Pacchiano , Moez Draief

We study the problem of estimating the average treatment effect (ATE) under sequentially adaptive treatment assignment mechanisms. In contrast to classical completely randomized designs, we consider a setting in which the probability of…

Statistics Theory · Mathematics 2026-05-12 Saikat Sengupta , Koulik Khamaru , Suvrojit Ghosh , Tirthankar Dasgupta

In reinforcement learning for partially observable environments, many successful algorithms have been developed within the asymmetric learning paradigm. This paradigm leverages additional state information available at training time for…

Machine Learning · Computer Science 2025-09-09 Gaspard Lambrechts , Damien Ernst , Aditya Mahajan

We study distributionally robust online learning, where a risk-averse learner updates decisions sequentially to guard against worst-case distributions drawn from a Wasserstein ambiguity set centered at past observations. While this paradigm…

Machine Learning · Computer Science 2026-02-25 Guixian Chen , Salar Fattahi , Soroosh Shafiee

Wasserstein distance plays increasingly important roles in machine learning, stochastic programming and image processing. Major efforts have been under way to address its high computational complexity, some leading to approximate or…

Machine Learning · Statistics 2019-06-26 Yujia Xie , Xiangfeng Wang , Ruijia Wang , Hongyuan Zha

We propose an actor-critic framework to solve the time-continuous stochastic optimal control problem. A least square temporal difference method is applied to compute the value function for the critic. The policy gradient method is…

Optimization and Control · Mathematics 2025-01-27 Mo Zhou , Jianfeng Lu