中文
相关论文

相关论文: HOPE: Human-Centric Off-Policy Evaluation for E-Le…

200 篇论文

We consider the off-policy evaluation (OPE) problem in contextual bandits, where the goal is to estimate the value of a target policy using the data collected by a logging policy. Most popular approaches to the OPE are variants of the…

机器学习 · 统计学 2024-08-20 Sutanoy Dasgupta , Yabo Niu , Kishan Panaganti , Dileep Kalathil , Debdeep Pati , Bani Mallick

We investigate the explainability of Reinforcement Learning (RL) policies from a temporal perspective, focusing on the sequence of future outcomes associated with individual actions. In RL, value functions compress information about rewards…

机器学习 · 计算机科学 2025-01-08 Franco Ruggeri , Alessio Russo , Rafia Inam , Karl Henrik Johansson

Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-world objectives--especially those derived from human preferences--are often uncertain,…

机器学习 · 计算机科学 2026-04-30 Disha Singha

Offline reinforcement learning (RL) shows promise of applying RL to real-world problems by effectively utilizing previously collected data. Most existing offline RL algorithms use regularization or constraints to suppress extrapolation…

机器学习 · 计算机科学 2021-10-20 Xiaoteng Ma , Yiqin Yang , Hao Hu , Qihan Liu , Jun Yang , Chongjie Zhang , Qianchuan Zhao , Bin Liang

Recent advancements in Reinforcement Learning with Verifiable Rewards (RLVR) have significantly improved Large Language Model (LLM) reasoning, yet models often struggle to explore novel trajectories beyond their initial policy distribution.…

人工智能 · 计算机科学 2026-05-28 Xinyu Ma , Mingzhou Xu , Xuebo Liu , Chang Jin , Qiang Wang , Derek F. Wong , Min Zhang

Off-policy evaluation (OPE) aims to accurately evaluate the performance of counterfactual policies using only offline logged data. Although many estimators have been developed, there is no single estimator that dominates the others, because…

机器学习 · 计算机科学 2023-01-31 Takuma Udagawa , Haruka Kiyohara , Yusuke Narita , Yuta Saito , Kei Tateno

Off-policy evaluation (OPE) in reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. We consider for the first time the semiparametric…

机器学习 · 计算机科学 2020-06-08 Nathan Kallus , Masatoshi Uehara

The problem of on-line off-policy evaluation (OPE) has been actively studied in the last decade due to its importance both as a stand-alone problem and as a module in a policy improvement scheme. However, most Temporal Difference (TD) based…

机器学习 · 统计学 2017-02-24 Assaf Hallak , Shie Mannor

Off-policy evaluation (OPE) and off-policy learning (OPL) are foundational for decision-making in offline contextual bandits. Recent advances in OPL primarily optimize OPE estimators with improved statistical properties, assuming that…

机器学习 · 统计学 2025-09-04 Imad Aouali , Otmane Sakhi

This work pioneers regret analysis of risk-sensitive reinforcement learning in partially observable environments with hindsight observation, addressing a gap in theoretical exploration. We introduce a novel formulation that integrates…

机器学习 · 计算机科学 2024-02-29 Tonghe Zhang , Yu Chen , Longbo Huang

We study how to improve large foundation vision-language-action (VLA) systems through online reinforcement learning (RL) in real-world settings. Central to this process is the value function, which provides learning signals to guide VLA…

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

机器学习 · 计算机科学 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli

We consider the problem of off-policy evaluation for reinforcement learning, where the goal is to estimate the expected reward of a target policy $\pi$ using offline data collected by running a logging policy $\mu$. Standard…

机器学习 · 计算机科学 2020-07-09 Ming Yin , Yu-Xiang Wang

Optimizing survival outcomes, such as patient survival or customer retention, is a critical objective in data-driven decision-making. Off-Policy Evaluation~(OPE) provides a powerful framework for assessing such decision-making policies…

统计方法学 · 统计学 2026-03-25 Kohsuke Kubota , Mitsuhiro Takahashi , Yuta Saito

We consider off-policy evaluation (OPE) in Partially Observable Markov Decision Processes, where the evaluation policy depends only on observable variables but the behavior policy depends on latent states (Tennenholtz et al. (2020a)). Prior…

机器学习 · 计算机科学 2021-09-23 Yash Nair , Nan Jiang

This paper investigates the off-policy evaluation (OPE) problem from a distributional perspective. Rather than focusing solely on the expectation of the total return, as in most existing OPE methods, we aim to estimate the entire return…

机器学习 · 统计学 2026-04-27 Qi Kuang , Chao Wang , Yuling Jiao , Fan Zhou

We consider estimation of a linear functional of the treatment effect using adaptively collected data. This task finds a variety of applications including the off-policy evaluation (\textsf{OPE}) in contextual bandits, and estimation of the…

机器学习 · 统计学 2024-11-21 Jeonghwan Lee , Cong Ma

Off-policy evaluation of sequential decision policies from observational data is necessary in applications of batch reinforcement learning such as education and healthcare. In such settings, however, unobserved variables confound observed…

机器学习 · 计算机科学 2020-07-14 Nathan Kallus , Angela Zhou

Hierarchical Reinforcement Learning (HRL) frameworks like Option-Critic (OC) and Multi-updates Option Critic (MOC) have introduced significant advancements in learning reusable options. However, these methods underperform in multi-goal…

We revisit Group Relative Policy Optimization (GRPO) in both on-policy and off-policy optimization regimes. Our motivation comes from recent work on off-policy Proximal Policy Optimization (PPO), which improves training stability, sampling…