{"total":117,"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":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653,"area":"wm"},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061,"area":null},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007,"area":"wm"},{"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":"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":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"1807.03858","title":"Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees","created":"2018-07-10","cited_by_count":140,"area":"wm"},{"id":"2105.08756","title":"Pathdreamer: A World Model for Indoor Navigation","created":"2021-05-18","cited_by_count":118,"area":"wm"},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114,"area":"driving"},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107,"area":"offlinerl"},{"id":"2102.05815","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","created":"2021-02-11","cited_by_count":91,"area":"offlinerl"},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","cited_by_count":58,"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":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2205.13817","title":"Iso-Dream: Isolating and Leveraging Noncontrollable Visual Dynamics in World Models","created":"2022-05-27","cited_by_count":53,"area":"wm"},{"id":"2106.04615","title":"Vector Quantized Models for Planning","created":"2021-06-08","cited_by_count":48,"area":null},{"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":"2208.09515","title":"Spectral Decomposition Representation for Reinforcement Learning","created":"2022-08-19","cited_by_count":36,"area":null},{"id":"2105.07593","title":"Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation","created":"2021-05-17","cited_by_count":34,"area":null},{"id":"2310.09629","title":"Adaptive Online Replanning with Diffusion Models","created":"2023-10-14","cited_by_count":34,"area":"diffusion"},{"id":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33,"area":null},{"id":"2204.01464","title":"Value Gradient weighted Model-Based Reinforcement Learning","created":"2022-04-04","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":"2306.15713","title":"Rethinking Closed-loop Training for Autonomous Driving","created":"2023-06-27","cited_by_count":29,"area":"driving"},{"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":"2111.03189","title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","created":"2021-11-04","cited_by_count":26,"area":null},{"id":"2112.01010","title":"Differentiable Spatial Planning using Transformers","created":"2021-12-02","cited_by_count":25,"area":null},{"id":"2203.15955","title":"Investigating the Properties of Neural Network Representations in Reinforcement Learning","created":"2022-03-30","cited_by_count":24,"area":null},{"id":"2108.01843","title":"Model-Based Opponent Modeling","created":"2021-08-04","cited_by_count":22,"area":null},{"id":"2310.00344","title":"HarmonyDream: Task Harmonization Inside World Models","created":"2023-09-30","cited_by_count":22,"area":"wm"},{"id":"2110.05442","title":"Neural Algorithmic Reasoners are Implicit Planners","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2405.05349","title":"Offline Model-Based Optimization via Policy-Guided Gradient Search","created":"2024-05-08","cited_by_count":19,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2111.14629","title":"Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions","created":"2021-11-29","cited_by_count":17,"area":"offlinerl"},{"id":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2206.12542","title":"Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning","created":"2022-06-25","cited_by_count":15,"area":null},{"id":"2305.17400","title":"Query-Policy Misalignment in Preference-Based Reinforcement Learning","created":"2023-05-27","cited_by_count":15,"area":null},{"id":"2404.18926","title":"Point Cloud Models Improve Visual Robustness in Robotic Learners","created":"2024-04-29","cited_by_count":14,"area":null},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","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":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13,"area":"deeprl"},{"id":"2206.02902","title":"Goal-Space Planning with Subgoal Models","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2102.07456","title":"Neuro-algorithmic Policies enable Fast Combinatorial Generalization","created":"2021-02-15","cited_by_count":11,"area":null},{"id":"2108.03213","title":"Temporally Abstract Partial Models","created":"2021-08-06","cited_by_count":11,"area":null},{"id":"2109.11178","title":"Hierarchies of Planning and Reinforcement Learning for Robot Navigation","created":"2021-09-23","cited_by_count":11,"area":null},{"id":"2310.03912","title":"RTDK-BO: High Dimensional Bayesian Optimization with Reinforced Transformer Deep kernels","created":"2023-10-05","cited_by_count":11,"area":null},{"id":"2201.09765","title":"Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning","created":"2022-01-24","cited_by_count":10,"area":null},{"id":"2102.12924","title":"Visualizing MuZero Models","created":"2021-02-25","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":"2211.13937","title":"Operator Splitting Value Iteration","created":"2022-11-25","cited_by_count":8,"area":null},{"id":"2303.16189","title":"Planning with Sequence Models through Iterative Energy Minimization","created":"2023-03-28","cited_by_count":8,"area":null},{"id":"2110.12840","title":"Self-Consistent Models and Values","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2306.00840","title":"What model does MuZero learn?","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2102.13265","title":"Robot Navigation in a Crowd by Integrating Deep Reinforcement Learning and Online Planning","created":"2021-02-26","cited_by_count":6,"area":null},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","cited_by_count":6,"area":null},{"id":"2112.04153","title":"Model-Value Inconsistency as a Signal for Epistemic Uncertainty","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","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":"2206.03674","title":"Integrating Symmetry into Differentiable Planning with Steerable Convolutions","created":"2022-06-08","cited_by_count":6,"area":null},{"id":"2210.13542","title":"Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2210.16877","title":"On Rate-Distortion Theory in Capacity-Limited Cognition & Reinforcement Learning","created":"2022-10-30","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":"2411.02446","title":"Learning World Models for Unconstrained Goal Navigation","created":"2024-11-03","cited_by_count":6,"area":"wm"},{"id":"2412.05766","title":"Policy-shaped prediction: avoiding distractions in model-based reinforcement learning","created":"2024-12-08","cited_by_count":6,"area":"deeprl"},{"id":"2506.17124","title":"When Can Model-Free Reinforcement Learning be Enough for Thinking?","created":"2025-06-20","cited_by_count":6,"area":"lr"},{"id":"2601.17067","title":"A Mechanistic View on Video Generation as World Models: State and Dynamics","created":"2026-01-22","cited_by_count":6,"area":"wm"},{"id":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"id":"2208.00659","title":"Model-based graph reinforcement learning for inductive traffic signal control","created":"2022-08-01","cited_by_count":5,"area":null},{"id":"1801.09624","title":"Learning the Reward Function for a Misspecified Model","created":"2018-01-29","cited_by_count":4,"area":"alignment"},{"id":"2108.05713","title":"Towards real-world navigation with deep differentiable planners","created":"2021-08-08","cited_by_count":4,"area":null},{"id":"2211.15839","title":"Continuous Neural Algorithmic Planners","created":"2022-11-29","cited_by_count":4,"area":null},{"id":"2303.14889","title":"Model-Based Reinforcement Learning with Isolated Imaginations","created":"2023-03-27","cited_by_count":4,"area":"wm"},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2305.14223","title":"Co-Learning Empirical Games and World Models","created":"2023-05-23","cited_by_count":4,"area":"wm"},{"id":"2402.07102","title":"An Empirical Study on the Power of Future Prediction in Partially Observable Environments","created":"2024-02-11","cited_by_count":4,"area":"deeprl"},{"id":"2606.01626","title":"IMWM: Intuition Models Complement World Models for Latent Planning","created":"2026-06-01","cited_by_count":4,"area":"wm"},{"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":"2401.10516","title":"Episodic Reinforcement Learning with Expanded State-reward Space","created":"2024-01-19","cited_by_count":3,"area":"deeprl"},{"id":"2405.11718","title":"Feasibility Consistent Representation Learning for Safe Reinforcement Learning","created":"2024-05-20","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":"2506.02612","title":"Simple, Good, Fast: Self-Supervised World Models Free of Baggage","created":"2025-06-03","cited_by_count":3,"area":"wm"},{"id":"2206.02025","title":"Between Rate-Distortion Theory & Value Equivalence in Model-Based Reinforcement Learning","created":"2022-06-04","cited_by_count":2,"area":null},{"id":"2211.00086","title":"Disentangled (Un)Controllable Features","created":"2022-10-31","cited_by_count":2,"area":null},{"id":"2301.10119","title":"Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learning","created":"2023-01-24","cited_by_count":2,"area":null},{"id":"2302.04250","title":"Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration","created":"2023-02-08","cited_by_count":2,"area":null},{"id":"2304.10590","title":"A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making","created":"2023-04-20","cited_by_count":2,"area":null},{"id":"2412.12024","title":"Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2505.22772","title":"Calibrated Value-Aware Model Learning with Probabilistic Environment Models","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2106.05535","title":"Differentiable Robust LQR Layers","created":"2021-06-10","cited_by_count":1,"area":"offlinerl"},{"id":"2106.14080","title":"Model-Advantage and Value-Aware Models for Model-Based Reinforcement Learning: Bridging the Gap in Theory and Practice","created":"2021-06-26","cited_by_count":1,"area":null},{"id":"2112.04684","title":"Trajectory-Constrained Deep Latent Visual Attention for Improved Local Planning in Presence of Heterogeneous Terrain","created":"2021-12-09","cited_by_count":1,"area":null},{"id":"2209.08169","title":"Value Summation: A Novel Scoring Function for MPC-based Model-based Reinforcement Learning","created":"2022-09-16","cited_by_count":1,"area":null},{"id":"2212.06001","title":"Reinforcement Learning and Tree Search Methods for the Unit Commitment Problem","created":"2022-12-12","cited_by_count":1,"area":null},{"id":"2306.08810","title":"Deep Generative Models for Decision-Making and Control","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2306.17366","title":"$\\lambda$-models: Effective Decision-Aware Reinforcement Learning with Latent Models","created":"2023-06-30","cited_by_count":1,"area":null}],"next_cursor":"100"}