{"total":160,"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":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061,"area":null},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636,"area":"offlinerl"},{"id":"2102.09544","title":"Combinatorial optimization and reasoning with graph neural networks","created":"2021-02-18","cited_by_count":268,"area":null},{"id":"2106.04537","title":"Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks","created":"2021-06-08","cited_by_count":117,"area":null},{"id":"2107.05612","title":"A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution","created":"2021-07-12","cited_by_count":91,"area":null},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2205.03195","title":"Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation","created":"2022-05-06","cited_by_count":61,"area":null},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","cited_by_count":58,"area":null},{"id":"2210.12209","title":"Motion Policy Networks","created":"2022-10-21","cited_by_count":55,"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":"2106.03273","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","created":"2021-06-06","cited_by_count":35,"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":"2308.07241","title":"Context-Aware Planning and Environment-Aware Memory for Instruction Following Embodied Agents","created":"2023-08-14","cited_by_count":33,"area":null},{"id":"2106.11365","title":"Distributed Heuristic Multi-Agent Path Finding with Communication","created":"2021-06-21","cited_by_count":32,"area":null},{"id":"2108.11092","title":"INVIGORATE: Interactive Visual Grounding and Grasping in Clutter","created":"2021-08-25","cited_by_count":32,"area":null},{"id":"2104.05565","title":"Survey on reinforcement learning for language processing","created":"2021-04-12","cited_by_count":31,"area":null},{"id":"2205.10816","title":"Chain of Thought Imitation with Procedure Cloning","created":"2022-05-22","cited_by_count":30,"area":"lr"},{"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":"2112.01010","title":"Differentiable Spatial Planning using Transformers","created":"2021-12-02","cited_by_count":25,"area":null},{"id":"2203.16910","title":"End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps","created":"2022-03-31","cited_by_count":22,"area":null},{"id":"2110.05442","title":"Neural Algorithmic Reasoners are Implicit Planners","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2306.03072","title":"Explore to Generalize in Zero-Shot RL","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2210.08864","title":"Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks","created":"2022-10-17","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":"2501.02709","title":"Horizon Generalization in Reinforcement Learning","created":"2025-01-06","cited_by_count":17,"area":"deeprl"},{"id":"2202.03735","title":"Navigating to Objects in Unseen Environments by Distance Prediction","created":"2022-02-08","cited_by_count":16,"area":null},{"id":"2410.09163","title":"Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Models","created":"2024-10-11","cited_by_count":16,"area":"deeprl"},{"id":"2102.11344","title":"HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solving","created":"2021-02-22","cited_by_count":15,"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":"2308.00887","title":"Factor Graph Neural Networks","created":"2023-08-02","cited_by_count":15,"area":null},{"id":"1909.06953","title":"Off-road Autonomous Vehicles Traversability Analysis and Trajectory Planning Based on Deep Inverse Reinforcement Learning","created":"2019-09-16","cited_by_count":13,"area":"offlinerl"},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2204.01571","title":"Coarse-to-Fine Q-attention with Learned Path Ranking","created":"2022-04-04","cited_by_count":13,"area":null},{"id":"2210.15206","title":"Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision","created":"2022-10-27","cited_by_count":13,"area":"synth"},{"id":"2212.06759","title":"Learning Robotic Navigation from Experience: Principles, Methods, and Recent Results","created":"2022-12-13","cited_by_count":13,"area":null},{"id":"2212.11730","title":"TransPath: Learning Heuristics For Grid-Based Pathfinding via Transformers","created":"2022-12-22","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":"2101.03834","title":"Closing the Planning-Learning Loop with Application to Autonomous Driving","created":"2021-01-11","cited_by_count":12,"area":"driving"},{"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":"2109.11178","title":"Hierarchies of Planning and Reinforcement Learning for Robot Navigation","created":"2021-09-23","cited_by_count":11,"area":null},{"id":"2212.02603","title":"Learning to Optimize in Model Predictive Control","created":"2022-12-05","cited_by_count":11,"area":null},{"id":"2305.16569","title":"Accelerating Value Iteration with Anchoring","created":"2023-05-26","cited_by_count":11,"area":null},{"id":"2102.07244","title":"Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS","created":"2021-02-14","cited_by_count":10,"area":null},{"id":"2106.02791","title":"Motion Planning Transformers: A Motion Planning Framework for Mobile Robots","created":"2021-06-05","cited_by_count":10,"area":null},{"id":"2212.02587","title":"Learning Sampling Distributions for Model Predictive Control","created":"2022-12-05","cited_by_count":10,"area":null},{"id":"2102.12924","title":"Visualizing MuZero Models","created":"2021-02-25","cited_by_count":9,"area":null},{"id":"2105.00642","title":"One Model to Rule them All: Towards Zero-Shot Learning for Databases","created":"2021-05-03","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":"2503.03921","title":"CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance","created":"2025-03-05","cited_by_count":9,"area":null},{"id":"2103.12476","title":"Differentiable Agent-Based Simulation for Gradient-Guided Simulation-Based Optimization","created":"2021-03-23","cited_by_count":8,"area":null},{"id":"2111.13997","title":"Learning Continuous Environment Fields via Implicit Functions","created":"2021-11-27","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":"2306.00616","title":"Progressive Learning for Physics-informed Neural Motion Planning","created":"2023-06-01","cited_by_count":8,"area":null},{"id":"2103.01009","title":"Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2109.11792","title":"Regularization Guarantees Generalization in Bayesian Reinforcement Learning through Algorithmic Stability","created":"2021-09-24","cited_by_count":7,"area":null},{"id":"2110.12840","title":"Self-Consistent Models and Values","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2212.01939","title":"Winning the CityLearn Challenge: Adaptive Optimization with Evolutionary Search under Trajectory-based Guidance","created":"2022-12-04","cited_by_count":7,"area":null},{"id":"2212.03978","title":"Learning Graph Search Heuristics","created":"2022-12-07","cited_by_count":7,"area":"offlinerl"},{"id":"2306.00840","title":"What model does MuZero learn?","created":"2023-06-01","cited_by_count":7,"area":null},{"id":"2101.07891","title":"A modular vision language navigation and manipulation framework for long horizon compositional tasks in indoor environment","created":"2021-01-19","cited_by_count":6,"area":null},{"id":"2102.02886","title":"Ivy: Templated Deep Learning for Inter-Framework Portability","created":"2021-02-04","cited_by_count":6,"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":"2105.01777","title":"PathBench: A Benchmarking Platform for Classical and Learned Path Planning Algorithms","created":"2021-05-04","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":"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":"2212.14538","title":"Transformer in Transformer as Backbone for Deep Reinforcement Learning","created":"2022-12-30","cited_by_count":6,"area":null},{"id":"2306.03857","title":"Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction","created":"2023-06-06","cited_by_count":6,"area":null},{"id":"2309.13043","title":"E(2)-Equivariant Graph Planning for Navigation","created":"2023-09-22","cited_by_count":6,"area":null},{"id":"2403.02107","title":"Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning","created":"2024-03-04","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":"2511.00033","title":"STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization","created":"2025-10-27","cited_by_count":6,"area":null},{"id":"2202.10600","title":"Myriad: a real-world testbed to bridge trajectory optimization and deep learning","created":"2022-02-22","cited_by_count":5,"area":null},{"id":"2210.08408","title":"Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding","created":"2022-10-16","cited_by_count":5,"area":null},{"id":"2404.02176","title":"Versatile Navigation under Partial Observability via Value-guided Diffusion Policy","created":"2024-04-01","cited_by_count":5,"area":"diffusion"},{"id":"1801.09624","title":"Learning the Reward Function for a Misspecified Model","created":"2018-01-29","cited_by_count":4,"area":"alignment"},{"id":"2105.00312","title":"Waypoint Planning Networks","created":"2021-05-01","cited_by_count":4,"area":null},{"id":"2106.03121","title":"End-to-End Neuro-Symbolic Architecture for Image-to-Image Reasoning Tasks","created":"2021-06-06","cited_by_count":4,"area":null},{"id":"2108.05713","title":"Towards real-world navigation with deep differentiable planners","created":"2021-08-08","cited_by_count":4,"area":null},{"id":"2207.02518","title":"Compositional Generalization in Grounded Language Learning via Induced Model Sparsity","created":"2022-07-06","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":"2303.13986","title":"Interpretable Motion Planner for Urban Driving via Hierarchical Imitation Learning","created":"2023-03-24","cited_by_count":4,"area":"driving"},{"id":"2410.14040","title":"WARPD: World model Assisted Reactive Policy Diffusion","created":"2024-10-17","cited_by_count":4,"area":"wm"},{"id":"2412.12237","title":"Equivariant Action Sampling for Reinforcement Learning and Planning","created":"2024-12-16","cited_by_count":4,"area":"deeprl"},{"id":"2505.15157","title":"Cascaded Diffusion Models for Neural Motion Planning","created":"2025-05-21","cited_by_count":4,"area":"diffusion"},{"id":"2101.00186","title":"Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning","created":"2021-01-01","cited_by_count":3,"area":"offlinerl"},{"id":"2208.08883","title":"Data-driven End-to-end Learning of Pole Placement Control for Nonlinear Dynamics via Koopman Invariant Subspaces","created":"2022-08-16","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":"2210.16956","title":"Reward Shaping Using Convolutional Neural Network","created":"2022-10-30","cited_by_count":3,"area":null},{"id":"2301.10289","title":"PushWorld: A benchmark for manipulation planning with tools and movable obstacles","created":"2023-01-24","cited_by_count":3,"area":null},{"id":"2302.04798","title":"Equivariant MuZero","created":"2023-02-09","cited_by_count":3,"area":"wm"},{"id":"2312.12869","title":"Parameterized Projected Bellman Operator","created":"2023-12-20","cited_by_count":3,"area":null},{"id":"2406.08404","title":"Scaling Value Iteration Networks to 5000 Layers for Extreme Long-Term Planning","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2506.02612","title":"Simple, Good, Fast: Self-Supervised World Models Free of Baggage","created":"2025-06-03","cited_by_count":3,"area":"wm"}],"next_cursor":"100"}