{"total":36,"rows":[{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"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":"2201.12417","title":"Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error","created":"2022-01-28","cited_by_count":32,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2211.13904","title":"Policy-Adaptive Estimator Selection for Off-Policy Evaluation","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2105.10148","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","created":"2021-05-21","cited_by_count":22,"area":null},{"id":"2106.15734","title":"UAV-assisted Online Machine Learning over Multi-Tiered Networks: A Hierarchical Nested Personalized Federated Learning Approach","created":"2021-06-29","cited_by_count":20,"area":null},{"id":"2311.18207","title":"Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation","created":"2023-11-30","cited_by_count":13,"area":null},{"id":"2112.12320","title":"Model Selection in Batch Policy Optimization","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2101.07781","title":"Minimax Off-Policy Evaluation for Multi-Armed Bandits","created":"2021-01-19","cited_by_count":9,"area":null},{"id":"2205.07394","title":"Sibyl: Adaptive and Extensible Data Placement in Hybrid Storage Systems Using Online Reinforcement Learning","created":"2022-05-15","cited_by_count":8,"area":null},{"id":"2210.15543","title":"Beyond the Return: Off-policy Function Estimation under User-specified Error-measuring Distributions","created":"2022-10-27","cited_by_count":8,"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":"2305.04073","title":"Explaining RL Decisions with Trajectories","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2310.17146","title":"Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2205.08716","title":"No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL","created":"2022-05-18","cited_by_count":6,"area":null},{"id":"2404.15084","title":"Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It","created":"2024-04-23","cited_by_count":5,"area":null},{"id":"2310.18212","title":"Robustness of Algorithms for Causal Structure Learning to Hyperparameter Choice","created":"2023-10-27","cited_by_count":4,"area":null},{"id":"2310.18409","title":"State-Action Similarity-Based Representations for Off-Policy Evaluation","created":"2023-10-27","cited_by_count":4,"area":null},{"id":"2106.03934","title":"Offline Policy Comparison under Limited Historical Agent-Environment Interactions","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2107.01360","title":"Supervised Off-Policy Ranking","created":"2021-07-03","cited_by_count":3,"area":null},{"id":"2111.00765","title":"Validate on Sim, Detect on Real -- Model Selection for Domain Randomization","created":"2021-11-01","cited_by_count":3,"area":null},{"id":"2205.10416","title":"ARLO: A Framework for Automated Reinforcement Learning","created":"2022-05-20","cited_by_count":3,"area":null},{"id":"2302.04810","title":"Machine Learning Systems: A Survey from a Data-Oriented Perspective","created":"2023-02-09","cited_by_count":3,"area":null},{"id":"2210.10048","title":"AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2302.14139","title":"Scalable End-to-End ML Platforms: from AutoML to Self-serve","created":"2023-02-27","cited_by_count":2,"area":null},{"id":"2606.25601","title":"Statistically Valid Post-Training Hyperparameter Selection: From Tuning to Guarantees","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2201.02300","title":"Hyperparameter Selection Methods for Fitted Q-Evaluation with Error Guarantee","created":"2022-01-07","cited_by_count":1,"area":null},{"id":"2209.14488","title":"Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2306.09800","title":"$\\pi2\\text{vec}$: Policy Representations with Successor Features","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2503.20507","title":"Harmonia: Enhancing Data Placement and Migration in Hybrid Storage Systems via Multi-Agent Reinforcement Learning","created":"2025-03-26","cited_by_count":1,"area":null},{"id":"2205.10739","title":"Offline Policy Comparison with Confidence: Benchmarks and Baselines","created":"2022-05-22","cited_by_count":0,"area":null},{"id":"2306.07741","title":"Stepsize Learning for Policy Gradient Methods in Contextual Markov Decision Processes","created":"2023-06-13","cited_by_count":0,"area":null},{"id":"2410.20017","title":"Off-Policy Selection for Initiating Human-Centric Experimental Design","created":"2024-10-26","cited_by_count":0,"area":null},{"id":"2503.15890","title":"Time After Time: Deep-Q Effect Estimation for Interventions on When and What to do","created":"2025-03-20","cited_by_count":0,"area":null},{"id":"2609.29549","title":"StepCOPS: Closed-Testing Lower-Tail Certificates for Language-Model Policy Selection","created":"2026-08-26","cited_by_count":0,"area":null}],"next_cursor":null}