{"total":121,"rows":[{"id":"2203.01387","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","created":"2022-03-02","cited_by_count":231,"area":"offlinerl"},{"id":"2106.08909","title":"Offline RL Without Off-Policy Evaluation","created":"2021-06-16","cited_by_count":151,"area":"offlinerl"},{"id":"2007.09055","title":"Hyperparameter Selection for Offline Reinforcement Learning","created":"2020-07-17","cited_by_count":114,"area":"offlinerl"},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2103.06326","title":"S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning","created":"2021-03-10","cited_by_count":85,"area":"offlinerl"},{"id":"2109.10813","title":"A Workflow for Offline Model-Free Robotic Reinforcement Learning","created":"2021-09-22","cited_by_count":69,"area":"offlinerl"},{"id":"2107.11003","title":"Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings","created":"2021-07-23","cited_by_count":68,"area":"offlinerl"},{"id":"2102.00714","title":"NeoRL: A Near Real-World Benchmark for Offline Reinforcement Learning","created":"2021-02-01","cited_by_count":63,"area":"offlinerl"},{"id":"2006.13888","title":"RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning","created":"2020-06-24","cited_by_count":57,"area":"offlinerl"},{"id":"2202.06317","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","created":"2022-02-13","cited_by_count":54,"area":null},{"id":"2406.11827","title":"WPO: Enhancing RLHF with Weighted Preference Optimization","created":"2024-06-17","cited_by_count":54,"area":"alignment"},{"id":"2102.03607","title":"Bootstrapping Fitted Q-Evaluation for Off-Policy Inference","created":"2021-02-06","cited_by_count":40,"area":"offlinerl"},{"id":"2305.08062","title":"Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling","created":"2023-05-14","cited_by_count":34,"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":"2108.13703","title":"Evaluating the Robustness of Off-Policy Evaluation","created":"2021-08-31","cited_by_count":32,"area":null},{"id":"2110.14000","title":"Towards Hyperparameter-free Policy Selection for Offline Reinforcement Learning","created":"2021-10-26","cited_by_count":32,"area":"offlinerl"},{"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":"2210.07006","title":"Sustainable Online Reinforcement Learning for Auto-bidding","created":"2022-10-13","cited_by_count":29,"area":null},{"id":"2207.00046","title":"Performative Reinforcement Learning","created":"2022-06-30","cited_by_count":27,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2311.03351","title":"Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization","created":"2023-11-06","cited_by_count":26,"area":"offlinerl"},{"id":"2110.04156","title":"Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters","created":"2021-10-08","cited_by_count":24,"area":"offlinerl"},{"id":"2110.12343","title":"Off-Policy Evaluation in Partially Observed Markov Decision Processes under Sequential Ignorability","created":"2021-10-24","cited_by_count":24,"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":"2208.04560","title":"Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems","created":"2022-08-09","cited_by_count":22,"area":"offlinerl"},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2102.10242","title":"Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach","created":"2021-02-20","cited_by_count":16,"area":null},{"id":"2103.02084","title":"Minimax Model Learning","created":"2021-03-02","cited_by_count":16,"area":null},{"id":"2109.08331","title":"Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation","created":"2021-09-17","cited_by_count":16,"area":"offlinerl"},{"id":"2203.04510","title":"ReVar: Strengthening Policy Evaluation via Reduced Variance Sampling","created":"2022-03-09","cited_by_count":16,"area":null},{"id":"2302.04334","title":"Asking for Help: Failure Prediction in Behavioral Cloning through Value Approximation","created":"2023-02-08","cited_by_count":16,"area":"offlinerl"},{"id":"2107.11927","title":"On Blame Attribution for Accountable Multi-Agent Sequential Decision Making","created":"2021-07-26","cited_by_count":13,"area":null},{"id":"2110.07699","title":"Safe Autonomous Racing via Approximate Reachability on Ego-vision","created":"2021-10-14","cited_by_count":13,"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":"2402.06151","title":"POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition","created":"2024-02-09","cited_by_count":13,"area":"deeprl"},{"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":"2206.02887","title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2210.08642","title":"Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data","created":"2022-10-16","cited_by_count":12,"area":"offlinerl"},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2312.01457","title":"Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits","created":"2023-12-03","cited_by_count":9,"area":null},{"id":"2404.15691","title":"Long-term Off-Policy Evaluation and Learning","created":"2024-04-24","cited_by_count":9,"area":null},{"id":"2103.06671","title":"Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks","created":"2021-03-11","cited_by_count":8,"area":"offlinerl"},{"id":"2210.05980","title":"Efficient Offline Policy Optimization with a Learned Model","created":"2022-10-12","cited_by_count":8,"area":"offlinerl"},{"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":"2405.18610","title":"DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment Regime","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"id":"2503.01134","title":"Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs","created":"2025-03-03","cited_by_count":8,"area":"deeprl"},{"id":"2204.03140","title":"Off-Policy Evaluation with Online Adaptation for Robot Exploration in Challenging Environments","created":"2022-04-07","cited_by_count":7,"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":"2310.17146","title":"Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2310.18715","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","created":"2023-10-28","cited_by_count":7,"area":"offlinerl"},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2204.12750","title":"DraftRec: Personalized Draft Recommendation for Winning in Multi-Player Online Battle Arena Games","created":"2022-04-27","cited_by_count":6,"area":null},{"id":"2210.13373","title":"Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2306.00972","title":"Improving and Benchmarking Offline Reinforcement Learning Algorithms","created":"2023-06-01","cited_by_count":6,"area":"offlinerl"},{"id":"2311.18206","title":"SCOPE-RL: A Python Library for Offline Reinforcement Learning and Off-Policy Evaluation","created":"2023-11-30","cited_by_count":6,"area":"offlinerl"},{"id":"2502.08021","title":"Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol","created":"2025-02-11","cited_by_count":6,"area":"offlinerl"},{"id":"2111.03936","title":"SOPE: Spectrum of Off-Policy Estimators","created":"2021-11-06","cited_by_count":5,"area":null},{"id":"2302.00141","title":"Revisiting Bellman Errors for Offline Model Selection","created":"2023-01-31","cited_by_count":5,"area":"offlinerl"},{"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":"2309.01807","title":"Marginalized Importance Sampling for Off-Environment Policy Evaluation","created":"2023-09-04","cited_by_count":5,"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":"2311.14110","title":"When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective","created":"2023-11-23","cited_by_count":4,"area":"alignment"},{"id":"2404.04714","title":"Data Poisoning Attacks on Off-Policy Policy Evaluation Methods","created":"2024-04-06","cited_by_count":4,"area":"safety"},{"id":"2406.19531","title":"Off-policy Evaluation with Deeply-abstracted States","created":"2024-06-27","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":"2111.14346","title":"Pessimistic Model Selection for Offline Deep Reinforcement Learning","created":"2021-11-29","cited_by_count":3,"area":"offlinerl"},{"id":"2203.03003","title":"Offline Deep Reinforcement Learning for Dynamic Pricing of Consumer Credit","created":"2022-03-06","cited_by_count":3,"area":"offlinerl"},{"id":"2206.02000","title":"Hybrid Value Estimation for Off-policy Evaluation and Offline Reinforcement Learning","created":"2022-06-04","cited_by_count":3,"area":"offlinerl"},{"id":"2307.07014","title":"Leveraging Factored Action Spaces for Off-Policy Evaluation","created":"2023-07-13","cited_by_count":3,"area":null},{"id":"2312.11551","title":"Probabilistic Offline Policy Ranking with Approximate Bayesian Computation","created":"2023-12-17","cited_by_count":3,"area":null},{"id":"2405.15332","title":"Cross-Validated Off-Policy Evaluation","created":"2024-05-24","cited_by_count":3,"area":null},{"id":"2405.17708","title":"OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2405.18792","title":"Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies","created":"2024-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2410.02172","title":"Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation","created":"2024-10-03","cited_by_count":3,"area":"deeprl"},{"id":"2412.08052","title":"CANDOR: Counterfactual ANnotated DOubly Robust Off-Policy Evaluation","created":"2024-12-11","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":"2302.09605","title":"Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning","created":"2023-02-19","cited_by_count":2,"area":"offlinerl"},{"id":"2302.14833","title":"Learning to Control Autonomous Fleets from Observation via Offline Reinforcement Learning","created":"2023-02-28","cited_by_count":2,"area":"offlinerl"},{"id":"2303.10180","title":"Towards Real-World Applications of Personalized Anesthesia Using Policy Constraint Q Learning for Propofol Infusion Control","created":"2023-03-17","cited_by_count":2,"area":null},{"id":"2306.04836","title":"$K$-Nearest-Neighbor Resampling for Off-Policy Evaluation in Stochastic Control","created":"2023-06-07","cited_by_count":2,"area":null},{"id":"2406.18022","title":"Automated Off-Policy Estimator Selection via Supervised Learning","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2407.19380","title":"Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment","created":"2024-07-28","cited_by_count":2,"area":null},{"id":"2411.04138","title":"NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2502.21304","title":"Clustering Context in Off-Policy Evaluation","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2505.20781","title":"STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation","created":"2025-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2507.06961","title":"Off-Policy Evaluation Under Nonignorable Missing Data","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2511.06111","title":"Guardian-regularized Safe Offline Reinforcement Learning for Smart Weaning of Mechanical Circulatory Devices","created":"2025-11-08","cited_by_count":2,"area":"offlinerl"},{"id":"2512.03354","title":"Breaking Determinism: Stochastic Modeling for Reliable Off-Policy Evaluation in Ad Auctions","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2512.23805","title":"Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2607.03386","title":"When Aggregate Alignment Misleads: Auditing Policy Repair Without Per-State Expert Actions","created":"2026-07-03","cited_by_count":2,"area":"agents"},{"id":"2201.00236","title":"Operator Deep Q-Learning: Zero-Shot Reward Transferring in Reinforcement Learning","created":"2022-01-01","cited_by_count":1,"area":null},{"id":"2302.11725","title":"Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments","created":"2023-02-23","cited_by_count":1,"area":null},{"id":"2502.11480","title":"Enhancing Offline Model-Based RL via Active Model Selection: A Bayesian Optimization Perspective","created":"2025-02-17","cited_by_count":1,"area":"offlinerl"},{"id":"2605.05863","title":"SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data","created":"2026-05-07","cited_by_count":1,"area":"deeprl"},{"id":"2606.05558","title":"Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents","created":"2026-06-04","cited_by_count":1,"area":"wm"},{"id":"2107.01407","title":"Optimality Inductive Biases and Agnostic Guidelines for Offline Reinforcement Learning","created":"2021-07-03","cited_by_count":0,"area":"offlinerl"},{"id":"2203.01758","title":"On Practical Reinforcement Learning: Provable Robustness, Scalability, and Statistical Efficiency","created":"2022-03-03","cited_by_count":0,"area":"offlinerl"},{"id":"2212.08302","title":"Safe Evaluation For Offline Learning: Are We Ready To Deploy?","created":"2022-12-16","cited_by_count":0,"area":null}],"next_cursor":"100"}