paper-with-me

홈 › Papers

Off-policy Evaluation with Deeply-abstracted States

2024-06-27 · Meiling Hao, Pingfan Su, Liyuan Hu, Zoltan Szabo, Qingyuan Zhao, Chengchun Shi

Off-policy evaluation (OPE) is crucial for assessing a target policy's impact offline before its deployment. However, achieving accurate OPE in large state spaces remains challenging. This paper studies state abstractions -- originally designed for policy learning -- in the context of OPE. Our contributions are three-fold: (i) We define a set of irrelevance conditions central to learning state abstractions for OPE, and derive a backward-model-irrelevance condition for achieving irrelevance in %sequential and (marginalized) importance sampling ratios by constructing a time-reversed Markov decision process (MDP). (ii) We propose a novel iterative procedure that sequentially projects the original state space into a smaller space, resulting in a deeply-abstracted state, which substantially simplifies the sample complexity of OPE arising from high cardinality. (iii) We prove the Fisher consistencies of various OPE estimators when applied to our proposed abstract state spaces.

📄 PDF Abstract BibTeX arXiv:2406.19531

Code (1)

pufffs/state-abstraction 공식 구현 pytorch

Tasks

Off-policy evaluation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Generation of Policy-Level Explanations for Reinforcement Learning

2019-05-28 · Nicholay Topin, Manuela Veloso

Though reinforcement learning has greatly benefited from the incorporation of neural networks, the inability to verify the correctness of such systems limits their use. Current work in explainable deep learning focuses o…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Deeply-Debiased Off-Policy Interval Estimation

2021-05-10 · Chengchun Shi, Runzhe Wan, Victor Chernozhukov, Rui Song

Off-policy evaluation learns a target policy's value with a historical dataset generated by a different behavior policy. In addition to a point estimate, many applications would benefit significantly from having a confid…

Off-policy evaluation

AUPO -- Abstracted Until Proven Otherwise: A Reward Distribution Based Abstraction Algorithm

2025-10-27 · Robin Schmöcker, Alexander Dockhorn, Bodo Rosenhahn arxiv

We introduce a novel, drop-in modification to Monte Carlo Tree Search's (MCTS) decision policy that we call AUPO. Comparisons based on a range of IPPC benchmark problems show that AUPO clearly outperforms MCTS. AUPO is a…

Visual Relationship Detection with Relative Location Mining

2019-11-02 · Hao Zhou, Chongyang Zhang, Chuanping Hu

Visual relationship detection, as a challenging task used to find and distinguish the interactions between object pairs in one image, has received much attention recently. In this work, we propose a novel visual relation…

Graph Neural NetworkObjectRelationship DetectionVisual Relationship Detection

Unveiling the Potential of Graph Neural Networks in SME Credit Risk Assessment

2024-09-23 · Bingyao Liu, Iris Li, Jianhua Yao, Yuan Chen 외

This paper takes the graph neural network as the technical framework, integrates the intrinsic connections between enterprise financial indicators, and proposes a model for enterprise credit risk assessment. The main res…

Graph Neural NetworkRepresentation Learning