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.
Taylor Expansion Policy Optimization
Batch Stationary Distribution Estimation
Off-Policy Evaluation and Learning for External Validity under a Covariate Shift
Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation
Debiased Off-Policy Evaluation for Recommendation Systems
Adaptive Estimator Selection for Off-Policy Evaluation
Double/Debiased Machine Learning for Dynamic Treatment Effects via g-Estimation
Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning
Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions
Minimax Value Interval for Off-Policy Evaluation and Policy Optimization
Safe Exploration for Optimizing Contextual Bandits
Asymptotically Efficient Off-Policy Evaluation for Tabular Reinforcement Learning
More Efficient Off-Policy Evaluation through Regularized Targeted Learning
Triply Robust Off-Policy Evaluation
Minimax Weight and Q-Function Learning for Off-Policy Evaluation
From Importance Sampling to Doubly Robust Policy Gradient
Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation
Adaptive Trade-Offs in Off-Policy Learning
Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling
Efficiently Breaking the Curse of Horizon in Off-Policy Evaluation with Double Reinforcement Learning
Off-Policy Evaluation in Partially Observable Environments
Efron-Stein PAC-Bayesian Inequalities
Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes
Doubly robust off-policy evaluation with shrinkage
Task Selection Policies for Multitask Learning
Expected Sarsa($λ$) with Control Variate for Variance Reduction
Balanced off-policy evaluation in general action spaces
Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning
Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
Off-Policy Evaluation via Off-Policy Classification
Defining Admissible Rewards for High Confidence Policy Evaluation
Semi-Parametric Efficient Policy Learning with Continuous Actions
Combining Parametric and Nonparametric Models for Off-Policy Evaluation
Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models
Privacy Preserving Off-Policy Evaluation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.