paper-with-me

Papers

Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol

2025-02-11 · Pai Liu, Lingfeng Zhao, Shivangi Agarwal, Jinghan Liu, Audrey Huang, Philip Amortila, Nan Jiang

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 incurs exponential variance (e.g., importance sampling) or has hyperparameters on their own (e.g., FQE and model-based). In this work we focus on hyperparameter tuning for OPE itself, which is even more under-investigated. Concretely, we select among candidate value functions ("model-free") or dynamics ("model-based") to best assess the performance of a target policy. We develop: (1) new model-free and model-based selectors with theoretical guarantees, and (2) a new experimental protocol for empirically evaluating them. Compared to the model-free protocol in prior works, our new protocol allows for more stable generation and better control of candidate value functions in an optimization-free manner, and evaluation of model-free and model-based methods alike. We exemplify the protocol on Gym-Hopper, and find that our new model-free selector, LSTD-Tournament, demonstrates promising empirical performance.

📄 PDF Abstract BibTeX arXiv:2502.08021

Code (0)

등록된 구현이 없습니다.

Tasks

Model SelectionOff-policy evaluationReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Attack Selection in Agentic AI Control Evaluations Meaningfully Decreases Safety

2026-06-03 · Catherine Ge-Wang, Tyler Crosse, Benjamin Hadad, Joachim Schaeffer 외 arxiv

An attacker that strategically chooses when to attack is much harder to catch than one that attacks indiscriminately. AI control is a safety framework for deploying capable but untrusted AI agents under the oversight of …

A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods

2022-10-03 · Tiago Salvador, Kilian Fatras, Ioannis Mitliagkas, Adam Oberman

Unsupervised Domain Adaptation (UDA) aims at classifying unlabeled target images leveraging source labeled ones. In this work, we consider the Partial Domain Adaptation (PDA) variant, where we have extra source classes n…

Domain AdaptationModel SelectionPartial Domain AdaptationUnsupervised Domain Adaptation

State Selection Algorithms and Their Impact on The Performance of Stateful Network Protocol Fuzzing

2021-12-24 · Dongge Liu, Van-Thuan Pham, Gidon Ernst, Toby Murray 외

The statefulness property of network protocol implementations poses a unique challenge for testing and verification techniques, including Fuzzing. Stateful fuzzers tackle this challenge by leveraging state models to part…

Evaluation Strategy of Time-series Anomaly Detection with Decay Function

2023-05-15 · Yongwan Gim, Kyushik Min

Recent algorithms of time-series anomaly detection have been evaluated by applying a Point Adjustment (PA) protocol. However, the PA protocol has a problem of overestimating the performance of the detection algorithms be…

Anomaly DetectionTime SeriesTime Series Anomaly Detection

Offline Policy Selection under Uncertainty

2020-12-12 · Mengjiao Yang, Bo Dai, Ofir Nachum, George Tucker 외

The presence of uncertainty in policy evaluation significantly complicates the process of policy ranking and selection in real-world settings. We formally consider offline policy selection as learning preferences over a …