paper-with-me

Papers

Characterization of Efficient Influence Function for Off-Policy Evaluation Under Optimal Policies

2025-05-20 · Haoyu Wei

Off-policy evaluation (OPE) provides a powerful framework for estimating the value of a counterfactual policy using observational data, without the need for additional experimentation. Despite recent progress in robust and efficient OPE across various settings, rigorous efficiency analysis of OPE under an estimated optimal policy remains limited. In this paper, we establish a concise characterization of the efficient influence function (EIF) for the value function under optimal policy within canonical Markov decision process models. Specifically, we provide the sufficient conditions for the existence of the EIF and characterize its expression. We also give the conditions under which the EIF does not exist.

📄 PDF Abstract BibTeX arXiv:2505.13809

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualOff-policy evaluation

Similar Papers 제목 키워드 기반

A Complete Characterization of Linear Estimators for Offline Policy Evaluation

2022-03-08 · Juan C. Perdomo, Akshay Krishnamurthy, Peter Bartlett, Sham Kakade

Offline policy evaluation is a fundamental statistical problem in reinforcement learning that involves estimating the value function of some decision-making policy given data collected by a potentially different policy. …

Decision Makingreinforcement-learningReinforcement Learning (RL)

Variance-Aware Off-Policy Evaluation with Linear Function Approximation

2021-06-22 · NeurIPS 2021 12 · Yifei Min, Tianhao Wang, Dongruo Zhou, Quanquan Gu

We study the off-policy evaluation (OPE) problem in reinforcement learning with linear function approximation, which aims to estimate the value function of a target policy based on the offline data collected by a behavio…

Off-policy evaluationReinforcement Learning (RL)

Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions

2022-10-27 · Audrey Huang, Nan Jiang

Off-policy evaluation often refers to two related tasks: estimating the expected return of a policy and estimating its value function (or other functions of interest, such as density ratios). While recent works on margin…

Off-policy evaluation

Continuous-time reinforcement learning for optimal switching over multiple regimes

2025-12-04 · Yijie Huang, Mengge Li, Xiang Yu, Zhou Zhou arxiv

This paper studies the continuous-time reinforcement learning (RL) for optimal switching problems across multiple regimes. We consider a type of exploratory formulation under entropy regularization where the agent random…

Reinforcement Learning

PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping

2023-12-19 · Nai-Chieh Huang, Ping-Chun Hsieh, Kuo-Hao Ho, I-Chen Wu

Proximal Policy Optimization algorithm employing a clipped surrogate objective (PPO-Clip) is a prominent exemplar of the policy optimization methods. However, despite its remarkable empirical success, PPO-Clip lacks theo…