SOTAVerified

Off-policy evaluation

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–110 of 265 papers

TitleStatusHype
Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling—0
Learning Action Embeddings for Off-Policy EvaluationCode0
Conformal Off-Policy Evaluation in Markov Decision Processes—0
On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples—0
Hallucinated Adversarial Control for Conservative Offline Policy EvaluationCode0
Balanced Off-Policy Evaluation for Personalized PricingCode0
HOPE: Human-Centric Off-Policy Evaluation for E-Learning and Healthcare—0
Post Reinforcement Learning InferenceCode0
STEEL: Singularity-aware Reinforcement Learning—0
Variational Latent Branching Model for Off-Policy EvaluationCode0
Show:102550
← PrevPage 11 of 27Next →

No leaderboard results yet.