Papers with Code 아카이브
Off-policy evaluation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
Off-policy Evaluation (OPE), or offline evaluation in general, evaluates the performance of hypothetical policies leveraging only offline log data. It is particularly useful in applications where the online interaction involves high stakes and expensive setting such as precision medicine and recommender systems.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation
Off-Policy Evaluation for Large Action Spaces via Policy Convolution
Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks
Robust Multi-Agent Reinforcement Learning by Mutual Information Regularization
Off-Policy Evaluation for Human Feedback
Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework
Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits
Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning
Distributional Off-Policy Evaluation for Slate Recommendations
Doubly Robust Estimator for Off-Policy Evaluation with Large Action Spaces
On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-$n$ Recommendation
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation
Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning
Leveraging Factored Action Spaces for Off-Policy Evaluation
Off-Policy Evaluation of Ranking Policies under Diverse User Behavior
Off-policy Evaluation in Doubly Inhomogeneous Environments
$K$-Nearest-Neighbor Resampling for Off-Policy Evaluation in Stochastic Control
Counterfactual Evaluation of Peer-Review Assignment Policies
Human Choice Prediction in Language-based Persuasion Games: Simulation-based Off-Policy Evaluation
Scalable and Safe Remediation of Defective Actions in Self-Learning Conversational Systems
Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling
Learning Action Embeddings for Off-Policy Evaluation
Conformal Off-Policy Evaluation in Markov Decision Processes
On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples
Hallucinated Adversarial Control for Conservative Offline Policy Evaluation
Balanced Off-Policy Evaluation for Personalized Pricing
HOPE: Human-Centric Off-Policy Evaluation for E-Learning and Healthcare
Post Reinforcement Learning Inference
STEEL: Singularity-aware Reinforcement Learning
Variational Latent Branching Model for Off-Policy Evaluation
Off-Policy Evaluation for Action-Dependent Non-Stationary Environments
Off-Policy Evaluation with Out-of-Sample Guarantees
Inference on Time Series Nonparametric Conditional Moment Restrictions Using General Sieves
Quantile Off-Policy Evaluation via Deep Conditional Generative Learning
An Instrumental Variable Approach to Confounded Off-Policy Evaluation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.