{"total":140,"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":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773,"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":"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":"1906.08649","title":"Exploring Model-based Planning with Policy Networks","created":"2019-06-20","cited_by_count":90,"area":"wm"},{"id":"2004.07804","title":"A Game Theoretic Framework for Model Based Reinforcement Learning","created":"2020-04-16","cited_by_count":73,"area":"wm"},{"id":"2205.02909","title":"RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks","created":"2022-05-05","cited_by_count":72,"area":"wm"},{"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":"2202.07789","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":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","cited_by_count":44,"area":"offlinerl"},{"id":"2302.11312","title":"Behavior Proximal Policy Optimization","created":"2023-02-22","cited_by_count":43,"area":"offlinerl"},{"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":"2102.09161","title":"On the Sample Complexity of Stability Constrained Imitation Learning","created":"2021-02-18","cited_by_count":38,"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":"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":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","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":"2204.01464","title":"Value Gradient weighted Model-Based Reinforcement Learning","created":"2022-04-04","cited_by_count":32,"area":null},{"id":"2305.17625","title":"Cross-Domain Policy Adaptation via Value-Guided Data Filtering","created":"2023-05-28","cited_by_count":31,"area":null},{"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":"2103.13842","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","created":"2021-03-25","cited_by_count":28,"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":"2310.19427","title":"Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans","created":"2023-10-30","cited_by_count":27,"area":"diffusion"},{"id":"2405.15369","title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","created":"2024-05-24","cited_by_count":25,"area":"deeprl"},{"id":"2105.03363","title":"Model-based Multi-agent Policy Optimization with Adaptive Opponent-wise Rollouts","created":"2021-05-07","cited_by_count":24,"area":null},{"id":"2111.11485","title":"A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning","created":"2021-11-22","cited_by_count":24,"area":null},{"id":"2310.03301","title":"Learning Energy Decompositions for Partial Inference of GFlowNets","created":"2023-10-05","cited_by_count":24,"area":null},{"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":"2108.01843","title":"Model-Based Opponent Modeling","created":"2021-08-04","cited_by_count":22,"area":null},{"id":"2310.19848","title":"Efficient Exploration in Continuous-time Model-based Reinforcement Learning","created":"2023-10-30","cited_by_count":22,"area":null},{"id":"2405.13290","title":"Theoretical Analysis of Meta Reinforcement Learning: Generalization Bounds and Convergence Guarantees","created":"2024-05-22","cited_by_count":22,"area":"deeprl"},{"id":"2309.15421","title":"Deep Learning in Deterministic Computational Mechanics","created":"2023-09-27","cited_by_count":21,"area":null},{"id":"2306.02865","title":"Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2407.01418","title":"RoboPack: Learning Tactile-Informed Dynamics Models for Dense Packing","created":"2024-07-01","cited_by_count":19,"area":null},{"id":"2210.07553","title":"Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate","created":"2022-10-14","cited_by_count":18,"area":null},{"id":"2405.06192","title":"Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning","created":"2024-05-10","cited_by_count":18,"area":"offlinerl"},{"id":"2405.19014","title":"Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption","created":"2024-05-29","cited_by_count":18,"area":"deeprl"},{"id":"2409.16784","title":"World Model-based Perception for Visual Legged Locomotion","created":"2024-09-25","cited_by_count":18,"area":"wm"},{"id":"2207.12141","title":"Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy","created":"2022-07-25","cited_by_count":17,"area":null},{"id":"2301.08502","title":"Plan To Predict: Learning an Uncertainty-Foreseeing Model for Model-Based Reinforcement Learning","created":"2023-01-20","cited_by_count":17,"area":null},{"id":"2103.02084","title":"Minimax Model Learning","created":"2021-03-02","cited_by_count":16,"area":null},{"id":"2112.07701","title":"Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning","created":"2021-12-14","cited_by_count":16,"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":"2107.07410","title":"PC-MLP: Model-based Reinforcement Learning with Policy Cover Guided Exploration","created":"2021-07-15","cited_by_count":14,"area":null},{"id":"2110.03244","title":"Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver","created":"2021-10-07","cited_by_count":14,"area":null},{"id":"2203.07322","title":"Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation","created":"2022-03-14","cited_by_count":14,"area":null},{"id":"2210.05922","title":"A Unified Framework for Alternating Offline Model Training and Policy Learning","created":"2022-10-12","cited_by_count":14,"area":"offlinerl"},{"id":"2210.08349","title":"When to Update Your Model: Constrained Model-based Reinforcement Learning","created":"2022-10-15","cited_by_count":14,"area":null},{"id":"2401.03306","title":"MOTO: Offline Pre-training to Online Fine-tuning for Model-based Robot Learning","created":"2024-01-06","cited_by_count":14,"area":"offlinerl"},{"id":"2105.06350","title":"MapGo: Model-Assisted Policy Optimization for Goal-Oriented Tasks","created":"2021-05-13","cited_by_count":13,"area":null},{"id":"2111.08550","title":"On Effective Scheduling of Model-based Reinforcement Learning","created":"2021-11-16","cited_by_count":13,"area":null},{"id":"2202.05244","title":"REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer","created":"2022-02-10","cited_by_count":13,"area":null},{"id":"2210.09256","title":"On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning","created":"2022-10-17","cited_by_count":13,"area":null},{"id":"2206.04384","title":"Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":12,"area":"wm"},{"id":"2102.06961","title":"PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators","created":"2021-02-13","cited_by_count":10,"area":"offlinerl"},{"id":"2405.17031","title":"Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":10,"area":"offlinerl"},{"id":"2201.10070","title":"MOORe: Model-based Offline-to-Online Reinforcement Learning","created":"2022-01-25","cited_by_count":9,"area":"offlinerl"},{"id":"2305.16483","title":"Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2402.10765","title":"Policy Learning for Off-Dynamics RL with Deficient Support","created":"2024-02-16","cited_by_count":9,"area":"deeprl"},{"id":"2506.00867","title":"Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning","created":"2025-06-01","cited_by_count":9,"area":"diffusion"},{"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":"2110.02414","title":"Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks","created":"2021-10-05","cited_by_count":8,"area":null},{"id":"2111.08067","title":"ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control","created":"2021-11-15","cited_by_count":8,"area":null},{"id":"2207.06559","title":"Scalable Model-based Policy Optimization for Decentralized Networked Systems","created":"2022-07-13","cited_by_count":7,"area":null},{"id":"2208.02204","title":"Efficiently Computing Nash Equilibria in Adversarial Team Markov Games","created":"2022-08-03","cited_by_count":7,"area":null},{"id":"2507.20499","title":"DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-domain Reinforcement Learning","created":"2025-07-28","cited_by_count":7,"area":"diffusion"},{"id":"2108.11645","title":"Robust Model-based Reinforcement Learning for Autonomous Greenhouse Control","created":"2021-08-26","cited_by_count":6,"area":null},{"id":"2110.07985","title":"On-Policy Model Errors in Reinforcement Learning","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2209.05530","title":"Model-based Reinforcement Learning with Multi-step Plan Value Estimation","created":"2022-09-12","cited_by_count":6,"area":null},{"id":"2302.03939","title":"Learning Interaction-aware Motion Prediction Model for Decision-making in Autonomous Driving","created":"2023-02-08","cited_by_count":6,"area":"driving"},{"id":"2306.15156","title":"Learning non-Markovian Decision-Making from State-only Sequences","created":"2023-06-27","cited_by_count":6,"area":"offlinerl"},{"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":"2401.05899","title":"Optimistic Model Rollouts for Pessimistic Offline Policy Optimization","created":"2024-01-11","cited_by_count":6,"area":"offlinerl"},{"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":"2410.04553","title":"Bisimulation metric for Model Predictive Control","created":"2024-10-06","cited_by_count":6,"area":"deeprl"},{"id":"2411.02446","title":"Learning World Models for Unconstrained Goal Navigation","created":"2024-11-03","cited_by_count":6,"area":"wm"},{"id":"2110.13621","title":"Model-based Reinforcement Learning for Service Mesh Fault Resiliency in a Web Application-level","created":"2021-10-21","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":"2102.11448","title":"MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning","created":"2021-02-23","cited_by_count":4,"area":null},{"id":"2311.18393","title":"Data-efficient Deep Reinforcement Learning for Vehicle Trajectory Control","created":"2023-11-30","cited_by_count":4,"area":null},{"id":"2505.16242","title":"Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies","created":"2025-05-22","cited_by_count":4,"area":"offlinerl"},{"id":"2102.09361","title":"Efficient Reinforcement Learning in Resource Allocation Problems Through Permutation Invariant Multi-task Learning","created":"2021-02-18","cited_by_count":3,"area":null},{"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":"2305.09943","title":"Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum","created":"2023-05-17","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":"2309.02157","title":"Model-based Offline Policy Optimization with Adversarial Network","created":"2023-09-05","cited_by_count":3,"area":"offlinerl"},{"id":"2309.14989","title":"Tempo Adaptation in Non-stationary Reinforcement Learning","created":"2023-09-26","cited_by_count":3,"area":null},{"id":"2401.10516","title":"Episodic Reinforcement Learning with Expanded State-reward Space","created":"2024-01-19","cited_by_count":3,"area":"deeprl"},{"id":"2405.17039","title":"BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation","created":"2024-05-27","cited_by_count":3,"area":"wm"},{"id":"2407.10967","title":"BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning","created":"2024-07-15","cited_by_count":3,"area":"offlinerl"},{"id":"2503.20139","title":"Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learning","created":"2025-03-26","cited_by_count":3,"area":"deeprl"},{"id":"2505.23003","title":"Hybrid Cross-domain Robust Reinforcement Learning","created":"2025-05-29","cited_by_count":3,"area":"deeprl"},{"id":"2512.15036","title":"Spectral Representation-based Reinforcement Learning","created":"2025-12-17","cited_by_count":3,"area":"deeprl"},{"id":"2603.15221","title":"ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving","created":"2026-03-16","cited_by_count":3,"area":"driving"}],"next_cursor":"100"}