{"total":23,"rows":[{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2110.01770","title":"Procedure Planning in Instructional Videos via Contextual Modeling and Model-based Policy Learning","created":"2021-10-05","cited_by_count":53,"area":null},{"id":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43,"area":null},{"id":"2107.02776","title":"Counterfactual Explanations in Sequential Decision Making Under Uncertainty","created":"2021-07-06","cited_by_count":37,"area":null},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33,"area":null},{"id":"2204.00956","title":"Model-Free and Model-Based Policy Evaluation when Causality is Uncertain","created":"2022-04-02","cited_by_count":12,"area":null},{"id":"2212.07486","title":"Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction","created":"2022-12-14","cited_by_count":7,"area":null},{"id":"2111.03936","title":"SOPE: Spectrum of Off-Policy Estimators","created":"2021-11-06","cited_by_count":5,"area":null},{"id":"2302.09212","title":"HOPE: Human-Centric Off-Policy Evaluation for E-Learning and Healthcare","created":"2023-02-18","cited_by_count":5,"area":null},{"id":"2402.14664","title":"Bayesian Off-Policy Evaluation and Learning for Large Action Spaces","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2105.11818","title":"SGD with Coordinate Sampling: Theory and Practice","created":"2021-05-25","cited_by_count":4,"area":null},{"id":"2306.15625","title":"Value-aware Importance Weighting for Off-policy Reinforcement Learning","created":"2023-06-27","cited_by_count":4,"area":null},{"id":"2309.04222","title":"Offline Recommender System Evaluation under Unobserved Confounding","created":"2023-09-08","cited_by_count":4,"area":null},{"id":"2406.19531","title":"Off-policy Evaluation with Deeply-abstracted States","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2107.01360","title":"Supervised Off-Policy Ranking","created":"2021-07-03","cited_by_count":3,"area":null},{"id":"2605.13907","title":"AIS: Adaptive Importance Sampling for Quantized RL","created":"2026-05-13","cited_by_count":3,"area":null},{"id":"2112.11532","title":"Off Environment Evaluation Using Convex Risk Minimization","created":"2021-12-21","cited_by_count":2,"area":null},{"id":"2209.07074","title":"On the Reuse Bias in Off-Policy Reinforcement Learning","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2111.11113","title":"Case-based off-policy policy evaluation using prototype learning","created":"2021-11-22","cited_by_count":1,"area":null},{"id":"2205.07250","title":"A cGAN Ensemble-based Uncertainty-aware Surrogate Model for Offline Model-based Optimization in Industrial Control Problems","created":"2022-05-15","cited_by_count":1,"area":null},{"id":"2301.03183","title":"Minimax Weight Learning for Absorbing MDPs","created":"2023-01-09","cited_by_count":0,"area":null},{"id":"2602.12379","title":"Deep Doubly Debiased Longitudinal Effect Estimation with ICE G-Computation","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2605.14284","title":"Smooth Multi-Policy Causal Effect Estimation in Longitudinal Settings","created":"2026-05-14","cited_by_count":0,"area":null}],"next_cursor":null}