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.
Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits
Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment
Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences
Balancing Immediate Revenue and Future Off-Policy Evaluation in Coupon Allocation
Off-policy Evaluation with Deeply-abstracted States
Automated Off-Policy Estimator Selection via Supervised Learning
Confident Natural Policy Gradient for Local Planning in $q_π$-realizable Constrained MDPs
Off-Policy Evaluation from Logged Human Feedback
A Fast Convergence Theory for Offline Decision Making
RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation
Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies
OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators
Cross-Validated Off-Policy Evaluation
Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning
Long-term Off-Policy Evaluation and Learning
Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It
Data Poisoning Attacks on Off-Policy Policy Evaluation Methods
Methodology for Interpretable Reinforcement Learning for Optimizing Mechanical Ventilation
Doubly-Robust Off-Policy Evaluation with Estimated Logging Policy
Predictive Performance Comparison of Decision Policies Under Confounding
Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes
Cramming Contextual Bandits for On-policy Statistical Evaluation
Bayesian Off-Policy Evaluation and Learning for Large Action Spaces
On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap
Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction
Distributional Off-policy Evaluation with Bellman Residual Minimization
Probabilistic Offline Policy Ranking with Approximate Bayesian Computation
RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health Interventions
Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits
SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation
Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation
When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective
Unbiased Offline Evaluation for Learning to Rank with Business Rules
Robust Offline Reinforcement learning with Heavy-Tailed Rewards
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.