{"total":162,"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":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644,"area":"wm"},{"id":"2002.08396","title":"Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning","created":"2020-02-19","cited_by_count":215,"area":"offlinerl"},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134,"area":null},{"id":"1802.09564","title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","created":"2018-02-26","cited_by_count":126,"area":"offlinerl"},{"id":"2109.13333","title":"Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients","created":"2021-09-27","cited_by_count":122,"area":"driving"},{"id":"2301.02328","title":"Extreme Q-Learning: MaxEnt RL without Entropy","created":"2023-01-05","cited_by_count":116,"area":"offlinerl"},{"id":"2108.08812","title":"Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning","created":"2021-08-19","cited_by_count":110,"area":"offlinerl"},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"id":"2204.07137","title":"Accelerated Policy Learning with Parallel Differentiable Simulation","created":"2022-04-14","cited_by_count":104,"area":null},{"id":"2105.12196","title":"From Motor Control to Team Play in Simulated Humanoid Football","created":"2021-05-25","cited_by_count":87,"area":null},{"id":"2202.00665","title":"Tutorial on amortized optimization","created":"2022-02-01","cited_by_count":83,"area":null},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53,"area":"rag"},{"id":"2604.23073","title":"RL Token: Bootstrapping Online RL with Vision-Language-Action Models","created":"2026-04-24","cited_by_count":49,"area":"vla"},{"id":"2203.09637","title":"Investigating Compounding Prediction Errors in Learned Dynamics Models","created":"2022-03-17","cited_by_count":47,"area":null},{"id":"1905.06750","title":"Random Expert Distillation: Imitation Learning via Expert Policy Support Estimation","created":"2019-05-16","cited_by_count":42,"area":"offlinerl"},{"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":"2211.02127","title":"Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation","created":"2022-11-03","cited_by_count":36,"area":null},{"id":"2302.09465","title":"Stochastic Generative Flow Networks","created":"2023-02-19","cited_by_count":32,"area":null},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"id":"2210.07573","title":"Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm","created":"2022-10-14","cited_by_count":29,"area":null},{"id":"2209.08466","title":"Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective","created":"2022-09-18","cited_by_count":28,"area":null},{"id":"2106.09119","title":"Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL","created":"2021-06-16","cited_by_count":24,"area":"offlinerl"},{"id":"2305.10912","title":"A Generalist Dynamics Model for Control","created":"2023-05-18","cited_by_count":24,"area":"wm"},{"id":"2108.00128","title":"Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control","created":"2021-07-31","cited_by_count":23,"area":null},{"id":"2112.10504","title":"Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic","created":"2021-12-16","cited_by_count":23,"area":null},{"id":"2201.12569","title":"Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes","created":"2022-01-29","cited_by_count":23,"area":null},{"id":"2408.05804","title":"A Single Goal is All You Need: Skills and Exploration Emerge from Contrastive RL without Rewards, Demonstrations, or Subgoals","created":"2024-08-11","cited_by_count":23,"area":null},{"id":"2109.14311","title":"Learning Dynamics Models for Model Predictive Agents","created":"2021-09-29","cited_by_count":22,"area":null},{"id":"2209.13052","title":"Training Efficient Controllers via Analytic Policy Gradient","created":"2022-09-26","cited_by_count":22,"area":null},{"id":"2309.15421","title":"Deep Learning in Deterministic Computational Mechanics","created":"2023-09-27","cited_by_count":21,"area":null},{"id":"2401.15866","title":"Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution","created":"2024-01-29","cited_by_count":21,"area":null},{"id":"2412.12089","title":"Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation","created":"2024-12-16","cited_by_count":20,"area":"deeprl"},{"id":"2502.07523","title":"Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization","created":"2025-02-11","cited_by_count":19,"area":"deeprl"},{"id":"2102.12611","title":"Improved Regret Bound and Experience Replay in Regularized Policy Iteration","created":"2021-02-25","cited_by_count":18,"area":null},{"id":"2108.05828","title":"A general class of surrogate functions for stable and efficient reinforcement learning","created":"2021-08-12","cited_by_count":18,"area":null},{"id":"2212.02179","title":"Physics-Informed Model-Based Reinforcement Learning","created":"2022-12-05","cited_by_count":18,"area":null},{"id":"2108.10273","title":"Collect & Infer -- a fresh look at data-efficient Reinforcement Learning","created":"2021-08-23","cited_by_count":17,"area":null},{"id":"2211.02222","title":"The Benefits of Model-Based Generalization in Reinforcement Learning","created":"2022-11-04","cited_by_count":17,"area":null},{"id":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2105.00371","title":"Discovering Diverse Athletic Jumping Strategies","created":"2021-05-02","cited_by_count":16,"area":null},{"id":"2106.05012","title":"Bayesian Bellman Operators","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2205.15795","title":"A Meta Reinforcement Learning Approach for Predictive Autoscaling in the Cloud","created":"2022-05-31","cited_by_count":16,"area":null},{"id":"2110.03363","title":"Evaluating model-based planning and planner amortization for continuous control","created":"2021-10-07","cited_by_count":15,"area":null},{"id":"2212.08765","title":"Latent Variable Representation for Reinforcement Learning","created":"2022-12-17","cited_by_count":15,"area":null},{"id":"2406.16121","title":"Diffusion Spectral Representation for Reinforcement Learning","created":"2024-06-23","cited_by_count":15,"area":"diffusion"},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2112.00597","title":"Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation","created":"2021-12-01","cited_by_count":13,"area":null},{"id":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"id":"2307.14993","title":"Thinker: Learning to Plan and Act","created":"2023-07-27","cited_by_count":13,"area":"wm"},{"id":"2505.00663","title":"Wasserstein Policy Optimization","created":"2025-05-01","cited_by_count":13,"area":"deeprl"},{"id":"2103.13887","title":"Adversarial Imitation Learning with Trajectorial Augmentation and Correction","created":"2021-03-25","cited_by_count":11,"area":"offlinerl"},{"id":"2201.12243","title":"Joint Differentiable Optimization and Verification for Certified Reinforcement Learning","created":"2022-01-28","cited_by_count":11,"area":null},{"id":"2305.17250","title":"Self-Supervised Reinforcement Learning that Transfers using Random Features","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2103.16977","title":"Solving Heterogeneous General Equilibrium Economic Models with Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":10,"area":null},{"id":"2402.05290","title":"Do Transformer World Models Give Better Policy Gradients?","created":"2024-02-07","cited_by_count":10,"area":"wm"},{"id":"2501.07468","title":"From Screens to Scenes: A Survey of Embodied AI in Healthcare","created":"2025-01-13","cited_by_count":10,"area":null},{"id":"2502.20168","title":"Accelerating Model-Based Reinforcement Learning with State-Space World Models","created":"2025-02-27","cited_by_count":10,"area":"wm"},{"id":"2103.05147","title":"Model-free Policy Learning with Reward Gradients","created":"2021-03-09","cited_by_count":9,"area":null},{"id":"2205.10868","title":"Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2505.23708","title":"AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learning","created":"2025-05-29","cited_by_count":9,"area":"deeprl"},{"id":"2102.04881","title":"Measuring Progress in Deep Reinforcement Learning Sample Efficiency","created":"2021-02-09","cited_by_count":8,"area":null},{"id":"2102.11513","title":"Mixed Policy Gradient: off-policy reinforcement learning driven jointly by data and model","created":"2021-02-23","cited_by_count":8,"area":null},{"id":"2302.03921","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2507.18809","title":"Test-time Offline Reinforcement Learning on Goal-related Experience","created":"2025-07-24","cited_by_count":8,"area":"offlinerl"},{"id":"2307.02728","title":"Hierarchical Empowerment: Towards Tractable Empowerment-Based Skill Learning","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2310.19927","title":"Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2507.11019","title":"Relative Entropy Pathwise Policy Optimization","created":"2025-07-15","cited_by_count":7,"area":"deeprl"},{"id":"2102.10456","title":"Decaying Clipping Range in Proximal Policy Optimization","created":"2021-02-20","cited_by_count":6,"area":null},{"id":"2110.10007","title":"Gradient-Based Mixed Planning with Symbolic and Numeric Action Parameters","created":"2021-10-19","cited_by_count":6,"area":null},{"id":"2204.09418","title":"Mingling Foresight with Imagination: Model-Based Cooperative Multi-Agent Reinforcement Learning","created":"2022-04-20","cited_by_count":6,"area":null},{"id":"2302.12617","title":"Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains","created":"2023-02-24","cited_by_count":6,"area":null},{"id":"2303.03955","title":"Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning","created":"2023-03-07","cited_by_count":6,"area":null},{"id":"2306.14133","title":"Provably Convergent Policy Optimization via Metric-aware Trust Region Methods","created":"2023-06-25","cited_by_count":6,"area":null},{"id":"2307.08863","title":"Meta-Value Learning: a General Framework for Learning with Learning Awareness","created":"2023-07-17","cited_by_count":6,"area":null},{"id":"2309.12671","title":"How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2310.01706","title":"On Representation Complexity of Model-based and Model-free Reinforcement Learning","created":"2023-10-03","cited_by_count":6,"area":null},{"id":"2410.02664","title":"Grounded Answers for Multi-agent Decision-making Problem through Generative World Model","created":"2024-10-03","cited_by_count":6,"area":"wm"},{"id":"2101.11331","title":"OffCon$^3$: What is state of the art anyway?","created":"2021-01-27","cited_by_count":5,"area":null},{"id":"2206.07536","title":"Autonomous Platoon Control with Integrated Deep Reinforcement Learning and Dynamic Programming","created":"2022-06-15","cited_by_count":5,"area":null},{"id":"2209.07676","title":"Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learning","created":"2022-09-16","cited_by_count":5,"area":null},{"id":"2402.02701","title":"Understanding What Affects the Generalization Gap in Visual Reinforcement Learning: Theory and Empirical Evidence","created":"2024-02-05","cited_by_count":5,"area":"deeprl"},{"id":"2403.04232","title":"Generalizing Cooperative Eco-driving via Multi-residual Task Learning","created":"2024-03-07","cited_by_count":5,"area":"driving"},{"id":"2509.00215","title":"First Order Model-Based RL through Decoupled Backpropagation","created":"2025-08-29","cited_by_count":5,"area":"deeprl"},{"id":"2104.00163","title":"DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation","created":"2021-03-31","cited_by_count":4,"area":"offlinerl"},{"id":"2202.02396","title":"A Temporal-Difference Approach to Policy Gradient Estimation","created":"2022-02-04","cited_by_count":4,"area":null},{"id":"2306.06754","title":"Reinforcement Learning in Robotic Motion Planning by Combined Experience-based Planning and Self-Imitation Learning","created":"2023-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2408.00309","title":"Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning","created":"2024-08-01","cited_by_count":4,"area":"deeprl"},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2105.05716","title":"Acting upon Imagination: when to trust imagined trajectories in model based reinforcement learning","created":"2021-05-12","cited_by_count":3,"area":null},{"id":"2106.01655","title":"Hierarchical Representation Learning for Markov Decision Processes","created":"2021-06-03","cited_by_count":3,"area":null},{"id":"2203.14660","title":"Revisiting Model-based Value Expansion","created":"2022-03-28","cited_by_count":3,"area":null},{"id":"2208.11535","title":"A model-based approach to meta-Reinforcement Learning: Transformers and tree search","created":"2022-08-24","cited_by_count":3,"area":null},{"id":"2305.15249","title":"Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2410.03915","title":"Distribution Guided Active Feature Acquisition","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2503.01178","title":"Differentiable Information Enhanced Model-Based Reinforcement Learning","created":"2025-03-03","cited_by_count":3,"area":"deeprl"}],"next_cursor":"100"}