https://github.com/st-tech/zr-obp
공식 코드Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation
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.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/tatsu432/DR-estimator-OPE-large-action
공식 코드Doubly Robust Estimator for Off-Policy Evaluation with Large Action Spaces
https://github.com/tgangwani/QDAgents
공식 코드Harnessing Distribution Ratio Estimators for Learning Agents with Quality and Diversity
https://github.com/thuml/TrajWorld
공식 코드https://github.com/tobiabir/hambo
공식 코드Hallucinated Adversarial Control for Conservative Offline Policy Evaluation
https://github.com/tobsutter/pmdi_dro
공식 코드Robust Generalization despite Distribution Shift via Minimum Discriminating Information
https://github.com/usaito/icml2022-mips
공식 코드Off-Policy Evaluation for Large Action Spaces via Embeddings
https://github.com/usaito/www2024-lope
공식 코드https://github.com/vanderschaarlab/mlforhealthlabpub/tree/main/alg/edm
공식 코드Strictly Batch Imitation Learning by Energy-based Distribution Matching
https://github.com/vsyrgkanis/policy_learning_continuous_actions
공식 코드Semi-Parametric Efficient Policy Learning with Continuous Actions
https://github.com/yashchandak/UnO
공식 코드https://github.com/yashchandak/activens
공식 코드Off-Policy Evaluation for Action-Dependent Non-Stationary Environments
https://github.com/yingchengyang/BIRIS
공식 코드https://github.com/yyzhangecnu/copp
공식 코드https://github.com/yzhao3685/pricing-evaluation
공식 코드https://github.com/zeyubian/2feope
공식 코드https://github.com/CausalML/IntrinsicallyEfficientStableOPE
Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning
https://github.com/CausalML/MultipleLoggers
Optimal Off-Policy Evaluation from Multiple Logging Policies
https://github.com/Leonardo-H/DR-PG
https://github.com/PlaytikaOSS/pybandits
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits
https://github.com/RetailMarketingAI/retailsynth-agentsim
Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation
https://github.com/bmazoure/batch_stationary_distribution
https://github.com/facebookresearch/Horizon
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits
https://github.com/facebookresearch/ReAgent
Optimal and Adaptive Off-policy Evaluation in Contextual Bandits
https://github.com/han20192019/newRL
Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation
https://github.com/hetankevin/mdpmix
Model-Free and Model-Based Policy Evaluation when Causality is Uncertain
https://github.com/liyuan9988/deepfeatureproxyvariable
Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation
https://github.com/microsoft/csrobust
https://github.com/tedmoskovitz/DOPE
https://github.com/tedmoskovitz/TOP
https://github.com/usaito/obp-demo
Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluation
https://github.com/valentyn1997/au-cnfs
https://github.com/yzhao3685/stoccontextualopti
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.