{"total":773,"rows":[{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920,"area":"offlinerl"},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546,"area":"offlinerl"},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644,"area":"wm"},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636,"area":"offlinerl"},{"id":"2005.05951","title":"MOReL : Model-Based Offline Reinforcement Learning","created":"2020-05-12","cited_by_count":590,"area":"offlinerl"},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397,"area":"wm"},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370,"area":"offlinerl"},{"id":"2601.16163","title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","created":"2026-01-22","cited_by_count":300,"area":"diffusion"},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288,"area":null},{"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":"2304.02948","title":"FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead","created":"2023-04-06","cited_by_count":175,"area":null},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174,"area":null},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170,"area":"wm"},{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166,"area":"wm"},{"id":"2106.04895","title":"Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning","created":"2021-06-09","cited_by_count":158,"area":"offlinerl"},{"id":"2405.15223","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","created":"2024-05-24","cited_by_count":146,"area":"wm"},{"id":"2508.05635","title":"Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation","created":"2025-08-07","cited_by_count":137,"area":"diffusion"},{"id":"2202.11566","title":"Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning","created":"2022-02-23","cited_by_count":125,"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":"2110.02034","title":"Dropout Q-Functions for Doubly Efficient Reinforcement Learning","created":"2021-10-05","cited_by_count":114,"area":null},{"id":"2505.15659","title":"FLARE: Robot Learning with Implicit World Modeling","created":"2025-05-21","cited_by_count":113,"area":"wm"},{"id":"2206.04745","title":"Mildly Conservative Q-Learning for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":112,"area":"offlinerl"},{"id":"2002.08550","title":"Learning to Walk in the Real World with Minimal Human Effort","created":"2020-02-20","cited_by_count":111,"area":"wm"},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104,"area":null},{"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":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"id":"2012.11547","title":"Offline Reinforcement Learning from Images with Latent Space Models","created":"2020-12-21","cited_by_count":95,"area":"offlinerl"},{"id":"2401.03360","title":"Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models","created":"2023-10-13","cited_by_count":91,"area":"diffusion"},{"id":"1906.08649","title":"Exploring Model-based Planning with Policy Networks","created":"2019-06-20","cited_by_count":90,"area":"wm"},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2601.03782","title":"PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation","created":"2026-01-07","cited_by_count":82,"area":"wm"},{"id":"2112.01388","title":"Residual Pathway Priors for Soft Equivariance Constraints","created":"2021-12-02","cited_by_count":75,"area":null},{"id":"2004.07804","title":"A Game Theoretic Framework for Model Based Reinforcement Learning","created":"2020-04-16","cited_by_count":73,"area":"wm"},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"area":null},{"id":"2011.12491","title":"World Model as a Graph: Learning Latent Landmarks for Planning","created":"2020-11-25","cited_by_count":69,"area":"wm"},{"id":"2202.06558","title":"Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation","created":"2022-02-14","cited_by_count":69,"area":null},{"id":"2202.07789","title":"Safe Reinforcement Learning by Imagining the Near Future","created":"2022-02-15","cited_by_count":67,"area":null},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2206.13452","title":"Causal Dynamics Learning for Task-Independent State Abstraction","created":"2022-06-27","cited_by_count":65,"area":null},{"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":"2110.05415","title":"Safe Reinforcement Learning Using Robust Control Barrier Functions","created":"2021-10-11","cited_by_count":59,"area":null},{"id":"2510.14830","title":"RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning","created":"2025-10-16","cited_by_count":59,"area":"deeprl"},{"id":"2201.09802","title":"Constrained Policy Optimization via Bayesian World Models","created":"2022-01-24","cited_by_count":57,"area":"wm"},{"id":"2401.00243","title":"Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles","created":"2023-12-30","cited_by_count":56,"area":"alignment"},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2501.10100","title":"Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics","created":"2025-01-17","cited_by_count":51,"area":"wm"},{"id":"2110.04135","title":"Revisiting Design Choices in Offline Model-Based Reinforcement Learning","created":"2021-10-08","cited_by_count":50,"area":"offlinerl"},{"id":"2205.11790","title":"Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning","created":"2022-05-24","cited_by_count":50,"area":"offlinerl"},{"id":"2207.07560","title":"Skill-based Model-based Reinforcement Learning","created":"2022-07-15","cited_by_count":50,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2403.00514","title":"Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning","created":"2024-03-01","cited_by_count":50,"area":"deeprl"},{"id":"2102.11492","title":"DeepThermal: Combustion Optimization for Thermal Power Generating Units Using Offline Reinforcement Learning","created":"2021-02-23","cited_by_count":48,"area":"offlinerl"},{"id":"2301.07784","title":"Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritization","created":"2023-01-18","cited_by_count":48,"area":null},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48,"area":"offlinerl"},{"id":"2110.00188","title":"Offline Reinforcement Learning with Reverse Model-based Imagination","created":"2021-10-01","cited_by_count":47,"area":"offlinerl"},{"id":"2203.09637","title":"Investigating Compounding Prediction Errors in Learned Dynamics Models","created":"2022-03-17","cited_by_count":47,"area":null},{"id":"2210.07241","title":"Visual Reinforcement Learning with Self-Supervised 3D Representations","created":"2022-10-13","cited_by_count":45,"area":null},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","cited_by_count":44,"area":"offlinerl"},{"id":"2210.11287","title":"MoCoDA: Model-based Counterfactual Data Augmentation","created":"2022-10-20","cited_by_count":44,"area":"offlinerl"},{"id":"2401.16635","title":"Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble","created":"2024-01-30","cited_by_count":44,"area":"alignment"},{"id":"2502.07825","title":"Pre-Trained Video Generative Models as World Simulators","created":"2025-02-10","cited_by_count":44,"area":null},{"id":"2604.03208","title":"Hierarchical Planning with Latent World Models","created":"2026-04-03","cited_by_count":43,"area":"wm"},{"id":"2104.05632","title":"Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment","created":"2021-04-12","cited_by_count":42,"area":"wm"},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42,"area":null},{"id":"2305.02968","title":"Masked Trajectory Models for Prediction, Representation, and Control","created":"2023-05-04","cited_by_count":42,"area":"offlinerl"},{"id":"2102.04764","title":"Continuous-Time Model-Based Reinforcement Learning","created":"2021-02-09","cited_by_count":41,"area":null},{"id":"2404.06356","title":"Policy-Guided Diffusion","created":"2024-04-09","cited_by_count":41,"area":"wm"},{"id":"2108.01846","title":"Learning Barrier Certificates: Towards Safe Reinforcement Learning with Zero Training-time Violations","created":"2021-08-04","cited_by_count":39,"area":null},{"id":"2109.07719","title":"Efficient Differentiable Simulation of Articulated Bodies","created":"2021-09-16","cited_by_count":39,"area":null},{"id":"2205.01758","title":"Differentiable Simulation of Soft Multi-body Systems","created":"2022-05-03","cited_by_count":39,"area":null},{"id":"2508.17600","title":"GWM: Towards Scalable Gaussian World Models for Robotic Manipulation","created":"2025-08-25","cited_by_count":39,"area":"wm"},{"id":"2310.17552","title":"Model-Based Runtime Monitoring with Interactive Imitation Learning","created":"2023-10-26","cited_by_count":38,"area":"offlinerl"},{"id":"2202.00728","title":"Physical Design using Differentiable Learned Simulators","created":"2022-02-01","cited_by_count":37,"area":null},{"id":"2206.08569","title":"Bootstrapped Transformer for Offline Reinforcement Learning","created":"2022-06-17","cited_by_count":37,"area":"offlinerl"},{"id":"2110.02758","title":"Mismatched No More: Joint Model-Policy Optimization for Model-Based RL","created":"2021-10-06","cited_by_count":36,"area":null},{"id":"2110.09796","title":"Offline Reinforcement Learning with Value-based Episodic Memory","created":"2021-10-19","cited_by_count":36,"area":"offlinerl"},{"id":"2304.10466","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","created":"2023-04-20","cited_by_count":36,"area":null},{"id":"2603.22078","title":"Do World Action Models Generalize Better than VLAs? A Robustness Study","created":"2026-03-23","cited_by_count":36,"area":"wm"},{"id":"2106.03273","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","created":"2021-06-06","cited_by_count":35,"area":null},{"id":"2312.10584","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data","created":"2023-12-17","cited_by_count":35,"area":"alignment"},{"id":"2105.12272","title":"Provable Representation Learning for Imitation with Contrastive Fourier Features","created":"2021-05-26","cited_by_count":34,"area":"offlinerl"},{"id":"2210.13846","title":"Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning","created":"2022-10-25","cited_by_count":34,"area":"offlinerl"},{"id":"2312.08533","title":"World Models via Policy-Guided Trajectory Diffusion","created":"2023-12-13","cited_by_count":34,"area":"wm"},{"id":"2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and Optimization","created":"2021-04-28","cited_by_count":33,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2107.05697","title":"Few-shot Language Coordination by Modeling Theory of Mind","created":"2021-07-12","cited_by_count":32,"area":null},{"id":"2204.01464","title":"Value Gradient weighted Model-Based Reinforcement Learning","created":"2022-04-04","cited_by_count":32,"area":null},{"id":"2402.06665","title":"The Essential Role of Causality in Foundation World Models for Embodied AI","created":"2024-02-06","cited_by_count":32,"area":"wm"},{"id":"2402.08848","title":"Hybrid Inverse Reinforcement Learning","created":"2024-02-13","cited_by_count":32,"area":"offlinerl"},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"id":"2202.04836","title":"Deconstructing the Inductive Biases of Hamiltonian Neural Networks","created":"2022-02-10","cited_by_count":31,"area":null},{"id":"2205.11027","title":"When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning","created":"2022-05-23","cited_by_count":31,"area":"offlinerl"},{"id":"2206.11403","title":"Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation","created":"2022-06-22","cited_by_count":31,"area":"wm"},{"id":"2305.17625","title":"Cross-Domain Policy Adaptation via Value-Guided Data Filtering","created":"2023-05-28","cited_by_count":31,"area":null},{"id":"2402.03570","title":"Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning","created":"2024-02-05","cited_by_count":31,"area":"wm"},{"id":"2508.03645","title":"DiWA: Diffusion Policy Adaptation with World Models","created":"2025-08-05","cited_by_count":31,"area":"wm"},{"id":"2105.07351","title":"Model-Based Offline Planning with Trajectory Pruning","created":"2021-05-16","cited_by_count":30,"area":"offlinerl"}],"next_cursor":"100"}