English
Related papers

Related papers: More Robust Doubly Robust Off-policy Evaluation

200 papers

Reinforcement learning (RL) agents are vulnerable to adversarial disturbances, which can deteriorate task performance or compromise safety specifications. Existing methods either address safety requirements under the assumption of no…

Machine Learning · Computer Science 2023-09-14 Zeyang Li , Chuxiong Hu , Yunan Wang , Yujie Yang , Shengbo Eben Li

Offline policy evaluation (OPE) allows us to evaluate and estimate a new sequential decision-making policy's performance by leveraging historical interaction data collected from other policies. Evaluating a new policy online without a…

Machine Learning · Computer Science 2024-11-04 Allen Nie , Yash Chandak , Christina J. Yuan , Anirudhan Badrinath , Yannis Flet-Berliac , Emma Brunskil

Offline Reinforcement Learning (RL) faces distributional shift and unreliable value estimation, especially for out-of-distribution (OOD) actions. To address this, existing uncertainty-based methods penalize the value function with…

Machine Learning · Computer Science 2024-04-10 Xudong Yu , Chenjia Bai , Hongyi Guo , Changhong Wang , Zhen Wang

Policy evaluation estimates the performance of a policy by (1) collecting data from the environment and (2) processing raw data into a meaningful estimate. Due to the sequential nature of reinforcement learning, any improper data-collecting…

Machine Learning · Computer Science 2025-03-21 Shuze Daniel Liu , Claire Chen , Shangtong Zhang

Distributionally robust reinforcement learning (DR-RL) has recently gained significant attention as a principled approach that addresses discrepancies between training and testing environments. To balance robustness, conservatism, and…

Machine Learning · Computer Science 2026-04-29 Zhenghao Li , Shengbo Wang , Nian Si

Holdout validation and hyperparameter tuning from data is a long-standing problem in offline reinforcement learning (RL). A standard framework is to use off-policy evaluation (OPE) methods to evaluate and select the policies, but OPE either…

Machine Learning · Computer Science 2025-10-27 Pai Liu , Lingfeng Zhao , Shivangi Agarwal , Jinghan Liu , Audrey Huang , Philip Amortila , Nan Jiang

Model-based reinforcement learning is a widely accepted solution for solving excessive sample demands. However, the predictions of the dynamics models are often not accurate enough, and the resulting bias may incur catastrophic decisions…

Machine Learning · Computer Science 2024-05-03 Wanpeng Zhang , Xi Xiao , Yao Yao , Mingzhe Chen , Dijun Luo

We investigate robustness to strong data corruption in offline sparse reinforcement learning (RL). In our setting, an adversary may arbitrarily perturb a fraction of the collected trajectories from a high-dimensional but sparse Markov…

Machine Learning · Statistics 2026-05-13 Nam Phuong Tran , Andi Nika , Goran Radanovic , Long Tran-Thanh , Debmalya Mandal

The Robust Regularized Markov Decision Process (RRMDP) is proposed to learn policies robust to dynamics shifts by adding regularization to the transition dynamics in the value function. Existing methods mostly use unstructured…

Machine Learning · Computer Science 2025-11-03 Cheng Tang , Zhishuai Liu , Pan Xu

We study the off-policy evaluation problem---estimating the value of a target policy using data collected by another policy---under the contextual bandit model. We consider the general (agnostic) setting without access to a consistent model…

Machine Learning · Statistics 2017-11-15 Yu-Xiang Wang , Alekh Agarwal , Miroslav Dudik

Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift. The learned policy may visit out-of-distribution state-action pairs…

Artificial Intelligence · Computer Science 2026-03-17 Hongqiang Lin , Zhenghui Fu , Weihao Tang , Pengfei Wang , Yiding Sun , Qixian Huang , Dongxu Zhang

This study tackles the challenges of adversarial corruption in model-based reinforcement learning (RL), where the transition dynamics can be corrupted by an adversary. Existing studies on corruption-robust RL mostly focus on the setting of…

Machine Learning · Statistics 2024-07-23 Chenlu Ye , Jiafan He , Quanquan Gu , Tong Zhang

Post-click conversion, as a strong signal indicating the user preference, is salutary for building recommender systems. However, accurately estimating the post-click conversion rate (CVR) is challenging due to the selection bias, i.e., the…

Machine Learning · Computer Science 2022-01-11 Siyuan Guo , Lixin Zou , Yiding Liu , Wenwen Ye , Suqi Cheng , Shuaiqiang Wang , Hechang Chen , Dawei Yin , Yi Chang

Policy gradients-based reinforcement learning has proven to be a promising approach for directly optimizing non-differentiable evaluation metrics for language generation tasks. However, optimizing for a specific metric reward leads to…

Computation and Language · Computer Science 2020-11-17 Ramakanth Pasunuru , Han Guo , Mohit Bansal

Distributionally robust optimization (DRO) and invariant risk minimization (IRM) are two popular methods proposed to improve out-of-distribution (OOD) generalization performance of machine learning models. While effective for small models,…

Machine Learning · Computer Science 2023-01-25 Xiao Zhou , Yong Lin , Renjie Pi , Weizhong Zhang , Renzhe Xu , Peng Cui , Tong Zhang

We study decision making in environments where the reward is only partially observed, but can be modeled as a function of an action and an observed context. This setting, known as contextual bandits, encompasses a wide variety of…

Machine Learning · Computer Science 2011-05-09 Miroslav Dudik , John Langford , Lihong Li

Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets without further environment interaction. A key challenge is the distribution shift between the learned and behavior policies, leading to…

Machine Learning · Computer Science 2025-08-11 Haohui Chen , Zhiyong Chen

In real life, we frequently come across data sets that involve some independent explanatory variable(s) generating a set of ordinal responses. These ordinal responses may correspond to an underlying continuous latent variable, which is…

Methodology · Statistics 2024-01-08 Arijit Pyne , Subhrajyoty Roy , Abhik Ghosh , Ayanendranath Basu

We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. A fundamental challenge behind this task is the distributional shift due to the dataset lacking sufficient exploration,…

Machine Learning · Computer Science 2023-10-11 Wenzhuo Zhou

Stationary Distribution Correction Estimation (DICE) addresses the mismatch between the stationary distribution induced by a policy and the target distribution required for reliable off-policy evaluation (OPE) and policy optimization.…

Machine Learning · Computer Science 2025-06-11 Woosung Kim , JunHo Seo , Jongmin Lee , Byung-Jun Lee
‹ Prev 1 8 9 10 Next ›