paper-with-me

홈 › Papers

Hyperparameter Selection Methods for Fitted Q-Evaluation with Error Guarantee

2022-01-07 · Kohei Miyaguchi

We are concerned with the problem of hyperparameter selection for the fitted Q-evaluation (FQE). FQE is one of the state-of-the-art method for offline policy evaluation (OPE), which is essential to the reinforcement learning without environment simulators. However, like other OPE methods, FQE is not hyperparameter-free itself and that undermines the utility in real-life applications. We address this issue by proposing a framework of approximate hyperparameter selection (AHS) for FQE, which defines a notion of optimality (called selection criteria) in a quantitative and interpretable manner without hyperparameters. We then derive four AHS methods each of which has different characteristics such as distribution-mismatch tolerance and time complexity. We also confirm in experiments that the error bound given by the theory matches empirical observations.

📄 PDF Abstract BibTeX arXiv:2201.02300

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient

2020-11-08 · Botao Hao, Yaqi Duan, Tor Lattimore, Csaba Szepesvári 외

This paper provides a statistical analysis of high-dimensional batch Reinforcement Learning (RL) using sparse linear function approximation. When there is a large number of candidate features, our result sheds light on t…

feature selectionModel Selectionreinforcement-learningReinforcement Learning+1

pared: Model selection using multi-objective optimization

2025-05-27 · Priyam Das, Sarah Robinson, Christine B. Peterson

Motivation: Model selection is a ubiquitous challenge in statistics. For penalized models, model selection typically entails tuning hyperparameters to maximize a measure of fit or minimize out-of-sample prediction error.…

modelModel Selection

Zero-shot Outlier Detection via Prior-data Fitted Networks: Model Selection Bygone!

2024-09-09 · Yuchen Shen, Haomin Wen, Leman Akoglu

Outlier detection (OD) has a vast literature as it finds numerous applications in environmental monitoring, cybersecurity, finance, and medicine to name a few. Being an inherently unsupervised task, model selection is a …

Model SelectionOutlier Detection

Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings

2021-07-23 · Shengpu Tang, Jenna Wiens

Reinforcement learning (RL) can be used to learn treatment policies and aid decision making in healthcare. However, given the need for generalization over complex state/action spaces, the incorporation of function approx…

Computational EfficiencyDecision MakingModel SelectionOffline RL+3

Span error bound for weighted SVM with applications in hyperparameter selection

2018-09-17 · Ioannis Sarafis, Christos Diou, Anastasios Delopoulos

Weighted SVM (or fuzzy SVM) is the most widely used SVM variant owning its effectiveness to the use of instance weights. Proper selection of the instance weights can lead to increased generalization performance. In this …