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.
Offline Comparison of Ranking Functions using Randomized Data
Efficient Counterfactual Learning from Bandit Feedback
Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy
Importance Sampling Policy Evaluation with an Estimated Behavior Policy
Counterfactual Mean Embeddings
More Robust Doubly Robust Off-policy Evaluation
Consistent On-Line Off-Policy Evaluation
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits
Large-scale Validation of Counterfactual Learning Methods: A Test-Bed
Bootstrapping with Models: Confidence Intervals for Off-Policy Evaluation
Off-policy evaluation for slate recommendation
Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis
Emphatic TD Bellman Operator is a Contraction
Off-policy evaluation for MDPs with unknown structure
On Minimax Optimal Offline Policy Evaluation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.