{"total":114,"rows":[{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899,"area":"offlinerl"},{"id":"2108.03298","title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","created":"2021-08-06","cited_by_count":725,"area":"offlinerl"},{"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":"2107.00591","title":"Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble","created":"2021-07-01","cited_by_count":214,"area":"offlinerl"},{"id":"2112.10751","title":"RvS: What is Essential for Offline RL via Supervised Learning?","created":"2021-12-20","cited_by_count":185,"area":"offlinerl"},{"id":"2106.08909","title":"Offline RL Without Off-Policy Evaluation","created":"2021-06-16","cited_by_count":151,"area":"offlinerl"},{"id":"2204.12581","title":"RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning","created":"2022-04-26","cited_by_count":115,"area":"offlinerl"},{"id":"2202.02446","title":"Adversarially Trained Actor Critic for Offline Reinforcement Learning","created":"2022-02-05","cited_by_count":111,"area":"offlinerl"},{"id":"2209.03993","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","created":"2022-09-08","cited_by_count":103,"area":"offlinerl"},{"id":"2201.13425","title":"Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning","created":"2022-01-31","cited_by_count":96,"area":"offlinerl"},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2207.10050","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","created":"2022-07-20","cited_by_count":89,"area":"offlinerl"},{"id":"2202.06239","title":"Supported Policy Optimization for Offline Reinforcement Learning","created":"2022-02-13","cited_by_count":74,"area":"offlinerl"},{"id":"2011.13885","title":"Offline Learning from Demonstrations and Unlabeled Experience","created":"2020-11-27","cited_by_count":72,"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":"2402.14606","title":"Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations","created":"2024-02-22","cited_by_count":53,"area":"offlinerl"},{"id":"2110.04135","title":"Revisiting Design Choices in Offline Model-Based Reinforcement Learning","created":"2021-10-08","cited_by_count":50,"area":"offlinerl"},{"id":"2302.11312","title":"Behavior Proximal Policy Optimization","created":"2023-02-22","cited_by_count":43,"area":"offlinerl"},{"id":"2102.03607","title":"Bootstrapping Fitted Q-Evaluation for Off-Policy Inference","created":"2021-02-06","cited_by_count":40,"area":"offlinerl"},{"id":"2103.04947","title":"Instabilities of Offline RL with Pre-Trained Neural Representation","created":"2021-03-08","cited_by_count":38,"area":"offlinerl"},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33,"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":"2102.09225","title":"Continuous Doubly Constrained Batch Reinforcement Learning","created":"2021-02-18","cited_by_count":27,"area":"offlinerl"},{"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":"2405.19673","title":"Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models","created":"2024-05-30","cited_by_count":25,"area":"diffusion"},{"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":"2207.02099","title":"An Empirical Study of Implicit Regularization in Deep Offline RL","created":"2022-07-05","cited_by_count":24,"area":"offlinerl"},{"id":"2211.13904","title":"Policy-Adaptive Estimator Selection for Off-Policy Evaluation","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2012.06899","title":"Semi-supervised reward learning for offline reinforcement learning","created":"2020-12-12","cited_by_count":23,"area":"alignment"},{"id":"2111.11097","title":"UMBRELLA: Uncertainty-Aware Model-Based Offline Reinforcement Learning Leveraging Planning","created":"2021-11-22","cited_by_count":23,"area":"offlinerl"},{"id":"2105.10148","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","created":"2021-05-21","cited_by_count":22,"area":null},{"id":"2406.17523","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning","created":"2024-06-25","cited_by_count":21,"area":"deeprl"},{"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":"2105.12034","title":"Hyperparameter Selection for Imitation Learning","created":"2021-05-25","cited_by_count":17,"area":"offlinerl"},{"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":"2210.03802","title":"Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization","created":"2022-10-07","cited_by_count":16,"area":"offlinerl"},{"id":"2211.02016","title":"Oracle Inequalities for Model Selection in Offline Reinforcement Learning","created":"2022-11-03","cited_by_count":13,"area":"offlinerl"},{"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":"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":"2112.12320","title":"Model Selection in Batch Policy Optimization","created":"2021-12-23","cited_by_count":11,"area":null},{"id":"2205.10629","title":"User-Interactive Offline Reinforcement Learning","created":"2022-05-21","cited_by_count":11,"area":"offlinerl"},{"id":"2306.10259","title":"Active Policy Improvement from Multiple Black-box Oracles","created":"2023-06-17","cited_by_count":11,"area":"offlinerl"},{"id":"2309.03081","title":"ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":11,"area":"offlinerl"},{"id":"2503.23513","title":"RARE: Retrieval-Augmented Reasoning Modeling","created":"2025-03-30","cited_by_count":11,"area":"lr"},{"id":"2504.11453","title":"A Clean Slate for Offline Reinforcement Learning","created":"2025-04-15","cited_by_count":11,"area":"offlinerl"},{"id":"2101.07781","title":"Minimax Off-Policy Evaluation for Multi-Armed Bandits","created":"2021-01-19","cited_by_count":9,"area":null},{"id":"2201.05433","title":"Comparing Model-free and Model-based Algorithms for Offline Reinforcement Learning","created":"2022-01-14","cited_by_count":9,"area":"offlinerl"},{"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":"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":"2301.11426","title":"Model-based Offline Reinforcement Learning with Local Misspecification","created":"2023-01-26","cited_by_count":5,"area":"offlinerl"},{"id":"2302.00141","title":"Revisiting Bellman Errors for Offline Model Selection","created":"2023-01-31","cited_by_count":5,"area":"offlinerl"},{"id":"2302.02788","title":"A Strong Baseline for Batch Imitation Learning","created":"2023-02-06","cited_by_count":5,"area":"offlinerl"},{"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":"2206.01085","title":"Incorporating Explicit Uncertainty Estimates into Deep Offline Reinforcement Learning","created":"2022-06-02","cited_by_count":4,"area":"offlinerl"},{"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":"2102.05612","title":"Personalization for Web-based Services using Offline Reinforcement Learning","created":"2021-02-10","cited_by_count":3,"area":"offlinerl"},{"id":"2104.10258","title":"Discovering an Aid Policy to Minimize Student Evasion Using Offline Reinforcement Learning","created":"2021-04-20","cited_by_count":3,"area":"offlinerl"},{"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":"2111.13461","title":"Measuring Data Quality for Dataset Selection in Offline Reinforcement Learning","created":"2021-11-26","cited_by_count":3,"area":"offlinerl"},{"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":"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":"2312.02355","title":"When is Offline Policy Selection Sample Efficient for Reinforcement Learning?","created":"2023-12-04","cited_by_count":3,"area":"offlinerl"},{"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":"2608.18669","title":"Reinforced Planning with Latent World Models","created":"2026-08-19","cited_by_count":2,"area":"wm"},{"id":"2110.03165","title":"Offline RL With Resource Constrained Online Deployment","created":"2021-10-07","cited_by_count":1,"area":"offlinerl"},{"id":"2112.09943","title":"Data Augmentation through Expert-guided Symmetry Detection to Improve Performance in Offline Reinforcement Learning","created":"2021-12-18","cited_by_count":1,"area":"offlinerl"},{"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":"2212.02620","title":"Benchmarking Offline Reinforcement Learning Algorithms for E-Commerce Order Fraud Evaluation","created":"2022-12-05","cited_by_count":1,"area":"offlinerl"},{"id":"2306.09800","title":"$\\pi2\\text{vec}$: Policy Representations with Successor Features","created":"2023-06-16","cited_by_count":1,"area":null},{"id":"2402.02858","title":"Deep autoregressive density nets vs neural ensembles for model-based offline reinforcement learning","created":"2024-02-05","cited_by_count":1,"area":"offlinerl"},{"id":"2410.19528","title":"AgentForge: A Flexible Low-Code Platform for Reinforcement Learning Agent Design","created":"2024-10-25","cited_by_count":1,"area":"deeprl"},{"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":"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":"2504.06683","title":"Hyperparameter Optimisation with Practical Interpretability and Explanation Methods in Probabilistic Curriculum Learning","created":"2025-04-09","cited_by_count":1,"area":"deeprl"},{"id":"2507.06404","title":"Learning to Evaluate Autonomous Behaviour in Human-Robot Interaction","created":"2025-07-08","cited_by_count":1,"area":"offlinerl"},{"id":"2602.00785","title":"World Models as an Intermediary between Agents and the Real World","created":"2026-01-31","cited_by_count":1,"area":"wm"},{"id":"2605.05123","title":"Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning","created":"2026-05-06","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":"2112.08094","title":"Automatic tuning of hyper-parameters of reinforcement learning algorithms using Bayesian optimization with behavioral cloning","created":"2021-12-15","cited_by_count":0,"area":"offlinerl"},{"id":"2205.10739","title":"Offline Policy Comparison with Confidence: Benchmarks and Baselines","created":"2022-05-22","cited_by_count":0,"area":null}],"next_cursor":"100"}