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/google-research/google-research

공식 코드

Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach

https://github.com/gsbDBI/contextual_bandits_evaluation

공식 코드

Off-Policy Evaluation via Adaptive Weighting with Data from Contextual Bandits

https://github.com/haanvid/kmifqe

공식 코드

Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies

https://github.com/haanvid/kmis

공식 코드

Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions

https://github.com/hakuhodo-technologies/scope-rl

공식 코드

SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation

https://github.com/hengruicai/djl

공식 코드

Deep Jump Learning for Off-Policy Evaluation in Continuous Treatment Settings

https://github.com/holarissun/Data-Centric-OPE

공식 코드

When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective

https://github.com/hse1223/distributional-ope-ebrm

공식 코드

Distributional Off-policy Evaluation with Bellman Residual Minimization

https://github.com/jakefawkes/dr_distributional_test

공식 코드

Doubly Robust Kernel Statistics for Testing Distributional Treatment Effects

https://github.com/jasonzhang929/BVFT_empirical_experiments

공식 코드

Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning

https://github.com/jiaweihhuang/confounded-pomdp-exp

공식 코드

A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes

https://github.com/kishanpb/offpolicyevaluation_informationborrowing_contextswitching

공식 코드

Off-Policy Evaluation Using Information Borrowing and Context-Based Switching

https://github.com/lguerdan/icml24_predictive_performance_comparison_dps

공식 코드

Predictive Performance Comparison of Decision Policies Under Confounding

https://github.com/mamba413/room

공식 코드

Robust Offline Reinforcement learning with Heavy-Tailed Rewards

https://github.com/mld3/counterfactualannot-semiope

공식 코드

Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation

https://github.com/msaveski/counterfactual-peer-review

공식 코드

Counterfactual Evaluation of Peer-Review Assignment Policies

https://github.com/navarog/cross-validated-ope

공식 코드

Cross-Validated Off-Policy Evaluation

https://github.com/olivierjeunen/ndcg-disagreement

공식 코드

On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-$n$ Recommendation

https://github.com/otmhi/offpolicy_ls

공식 코드

Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning

https://github.com/pearl-utexas/sope

공식 코드

SOPE: Spectrum of Off-Policy Estimators

https://github.com/pmdidro/PMDI_DRO

공식 코드

Robust Generalization despite Distribution Shift via Minimum Discriminating Information

https://github.com/pufffs/state-abstraction

공식 코드

Off-policy Evaluation with Deeply-abstracted States

https://github.com/rjagerman/tois2019-safe-exploration-algorithm

공식 코드

Safe Exploration for Optimizing Contextual Bandits

https://github.com/robintyh1/neurips2021-meta-gradient-offpolicy-evaluation

공식 코드

Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation

https://github.com/runzhestat/causalmarl

공식 코드

A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided Markets

https://github.com/ruohanzhan/rl_inference

공식 코드

Post Reinforcement Learning Inference

https://github.com/ryanxhr/por

공식 코드

A Policy-Guided Imitation Approach for Offline Reinforcement Learning

https://github.com/sfujim/SR-DICE

공식 코드

A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation

https://github.com/shreyasc-13/star

공식 코드

Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation

https://github.com/shreyasc-13/suno

공식 코드

Distributional Off-Policy Evaluation for Slate Recommendations

https://github.com/shutech2001/DOLCE

공식 코드

DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current Effects

https://github.com/skandavaidyanath/credit-assignment

공식 코드

Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning

https://github.com/sofiaek/off-policy-evaluation

공식 코드

Off-Policy Evaluation with Out-of-Sample Guarantees

https://github.com/sony/ds-research-code

공식 코드

Policy-Adaptive Estimator Selection for Off-Policy Evaluation

https://github.com/sony/pyieoe

공식 코드

Evaluating the Robustness of Off-Policy Evaluation

https://github.com/spotify-research/RIPS_KDD2020

공식 코드

Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactions

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