Papers with Code 아카이브

Off-policy evaluation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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.

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/CausalML/DoubleReinforcementLearningMDP

공식 코드

Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes

https://github.com/Kapilan-Balagopalan/Linear-Bandit-Algorithms

공식 코드

Minimum Empirical Divergence for Sub-Gaussian Linear Bandits

https://github.com/LARG/regression-importance-sampling

공식 코드

Importance Sampling Policy Evaluation with an Estimated Behavior Policy

https://github.com/MLD3/OfflineRL_ModelSelection

공식 코드

Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings

https://github.com/MasaKat0/OPE_CS

공식 코드

Off-Policy Evaluation and Learning for External Validity under a Covariate Shift

https://github.com/RunzheStat/D2OPE

공식 코드

Deeply-Debiased Off-Policy Interval Estimation

https://github.com/SOPR-T/SOPR-T

공식 코드

Supervised Off-Policy Ranking

https://github.com/VowpalWabbit/slope-experiments

공식 코드

Adaptive Estimator Selection for Off-Policy Evaluation

https://github.com/adith387/slates_semisynth_expts

공식 코드

Off-policy evaluation for slate recommendation

https://github.com/ai4ai-lab/factored-action-spaces-for-ope

공식 코드

Leveraging Factored Action Spaces for Off-Policy Evaluation

https://github.com/aiueola/kdd2023-aips

공식 코드

Off-Policy Evaluation of Ranking Policies under Diverse User Behavior

https://github.com/aiueola/neurips2023-future-dependent-ope

공식 코드

Future-Dependent Value-Based Off-Policy Evaluation in POMDPs

https://github.com/aiueola/webconf2024-slate-ope-via-abstraction

공식 코드

Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction

https://github.com/aiueola/wsdm2022-cascade-dr

공식 코드

Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model

https://github.com/albicaron/counterdkl

공식 코드

Counterfactual Learning with Multioutput Deep Kernels

https://github.com/amazon-science/ope-learn-action-embeddings

공식 코드

Learning Action Embeddings for Off-Policy Evaluation

https://github.com/anonymconference/knnr

공식 코드

$K$-Nearest-Neighbor Resampling for Off-Policy Evaluation in Stochastic Control

https://github.com/badger-rl/rope

공식 코드

State-Action Similarity-Based Representations for Off-Policy Evaluation

https://github.com/big-s2/causal-deepsets

공식 코드

Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences

https://github.com/bossdm/importancesampling

공식 코드

Low Variance Off-policy Evaluation with State-based Importance Sampling

https://github.com/causalml/adversarial-ope

공식 코드

Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes

https://github.com/causalml/doubly-robust-dropel

공식 코드

Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning

https://github.com/causalml/proximalrl

공식 코드

Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes

https://github.com/clinicalml/gumbel-max-scm

공식 코드

Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models

https://github.com/davidbrandfonbrener/onestep-rl

공식 코드

Offline RL Without Off-Policy Evaluation

https://github.com/deepmind/active_ops

공식 코드

Active Offline Policy Selection

https://github.com/deepmind/constrained_optidice

공식 코드

COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation

https://github.com/deepmind/offpolicy_selection_eslb

공식 코드

Confident Off-Policy Evaluation and Selection through Self-Normalized Importance Weighting

https://github.com/dtak/osiris

공식 코드

State Relevance for Off-Policy Evaluation

https://github.com/eastonhuch/rome

공식 코드

RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health Interventions

https://github.com/eilamshapira/humanchoiceprediction

공식 코드

Human Choice Prediction in Language-based Persuasion Games: Simulation-based Off-Policy Evaluation

https://github.com/faaizt/mr-ope

공식 코드

Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits

https://github.com/fernandoamat/slateope

공식 코드

Control Variates for Slate Off-Policy Evaluation

https://github.com/fsmiu/Two-way-Deconfounder

공식 코드

Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning

https://github.com/gaoqitong/vlbm

공식 코드

Variational Latent Branching Model for Off-Policy Evaluation

https://github.com/google-research/deep_ope

공식 코드

Benchmarks for Deep Off-Policy Evaluation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.