{"total":140,"rows":[{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636,"area":"offlinerl"},{"id":"2503.07536","title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","created":"2025-03-10","cited_by_count":248,"area":"lr"},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2308.10901","title":"Structured World Models from Human Videos","created":"2023-08-21","cited_by_count":147,"area":"wm"},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103,"area":null},{"id":"2102.05815","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","created":"2021-02-11","cited_by_count":91,"area":"offlinerl"},{"id":"2308.07498","title":"DREAMWALKER: Mental Planning for Continuous Vision-Language Navigation","created":"2023-08-14","cited_by_count":85,"area":"wm"},{"id":"2302.05817","title":"Level Generation Through Large Language Models","created":"2023-02-11","cited_by_count":68,"area":null},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66,"area":"wm"},{"id":"2103.01950","title":"Predicting Video with VQVAE","created":"2021-03-02","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":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2202.08417","title":"Retrieval-Augmented Reinforcement Learning","created":"2022-02-17","cited_by_count":53,"area":"rag"},{"id":"2107.12544","title":"Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning","created":"2021-07-27","cited_by_count":43,"area":null},{"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":"2203.04098","title":"COLA: Consistent Learning with Opponent-Learning Awareness","created":"2022-03-08","cited_by_count":38,"area":null},{"id":"2208.09515","title":"Spectral Decomposition Representation for Reinforcement Learning","created":"2022-08-19","cited_by_count":36,"area":null},{"id":"2301.05832","title":"World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges","created":"2023-01-14","cited_by_count":36,"area":"wm"},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"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":"2103.13834","title":"Self-Imitation Learning by Planning","created":"2021-03-25","cited_by_count":26,"area":"offlinerl"},{"id":"2511.07732","title":"ViPRA: Video Prediction for Robot Actions","created":"2025-11-11","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":"2505.11528","title":"LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation","created":"2025-05-13","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":"2108.11204","title":"Subgoal Search For Complex Reasoning Tasks","created":"2021-08-25","cited_by_count":21,"area":null},{"id":"2110.05442","title":"Neural Algorithmic Reasoners are Implicit Planners","created":"2021-10-11","cited_by_count":21,"area":null},{"id":"2512.16848","title":"Meta-RL Induces Exploration in Language Agents","created":"2025-12-18","cited_by_count":21,"area":"lr"},{"id":"2103.04693","title":"Unsupervised Object-Based Transition Models for 3D Partially Observable Environments","created":"2021-03-08","cited_by_count":20,"area":null},{"id":"2103.11505","title":"Policy-Guided Heuristic Search with Guarantees","created":"2021-03-21","cited_by_count":20,"area":null},{"id":"2107.00783","title":"Reinforcement Learning for Feedback-Enabled Cyber Resilience","created":"2021-07-02","cited_by_count":19,"area":null},{"id":"2202.05839","title":"Abstraction for Deep Reinforcement Learning","created":"2022-02-10","cited_by_count":19,"area":null},{"id":"2211.02147","title":"A Survey on Reinforcement Learning in Aviation Applications","created":"2022-11-03","cited_by_count":19,"area":null},{"id":"2106.04480","title":"There Is No Turning Back: A Self-Supervised Approach for Reversibility-Aware Reinforcement Learning","created":"2021-06-08","cited_by_count":18,"area":null},{"id":"2208.14226","title":"Unsupervised Representation Learning in Deep Reinforcement Learning: A Review","created":"2022-08-27","cited_by_count":18,"area":null},{"id":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2107.03961","title":"Computational Benefits of Intermediate Rewards for Goal-Reaching Policy Learning","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2506.01622","title":"General agents contain world models","created":"2025-06-02","cited_by_count":17,"area":"wm"},{"id":"2603.08561","title":"RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback","created":"2026-03-09","cited_by_count":17,"area":null},{"id":"2103.08255","title":"Sample-efficient Reinforcement Learning Representation Learning with Curiosity Contrastive Forward Dynamics Model","created":"2021-03-15","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":"2301.12962","title":"Hierarchical Imitation Learning with Vector Quantized Models","created":"2023-01-30","cited_by_count":15,"area":"offlinerl"},{"id":"2301.06294","title":"Neuro-Symbolic World Models for Adapting to Open World Novelty","created":"2023-01-16","cited_by_count":14,"area":"wm"},{"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":"2206.02902","title":"Goal-Space Planning with Subgoal Models","created":"2022-06-06","cited_by_count":12,"area":null},{"id":"2503.07671","title":"Probabilistic Shielding for Safe Reinforcement Learning","created":"2025-03-09","cited_by_count":12,"area":"deeprl"},{"id":"2102.07456","title":"Neuro-algorithmic Policies enable Fast Combinatorial Generalization","created":"2021-02-15","cited_by_count":11,"area":null},{"id":"2107.01715","title":"Improve Agents without Retraining: Parallel Tree Search with Off-Policy Correction","created":"2021-07-04","cited_by_count":10,"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":"2204.09597","title":"Perceiving the World: Question-guided Reinforcement Learning for Text-based Games","created":"2022-03-20","cited_by_count":10,"area":null},{"id":"2310.18247","title":"Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning","created":"2023-10-27","cited_by_count":10,"area":"offlinerl"},{"id":"2409.14216","title":"R-AIF: Solving Sparse-Reward Robotic Tasks from Pixels with Active Inference and World Models","created":"2024-09-21","cited_by_count":10,"area":"wm"},{"id":"2110.00898","title":"A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances","created":"2021-10-03","cited_by_count":9,"area":null},{"id":"2112.11490","title":"Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding","created":"2021-12-21","cited_by_count":9,"area":null},{"id":"2208.07123","title":"Online 3D Bin Packing Reinforcement Learning Solution with Buffer","created":"2022-08-15","cited_by_count":8,"area":null},{"id":"2212.12669","title":"On Realization of Intelligent Decision-Making in the Real World: A Foundation Decision Model Perspective","created":"2022-12-24","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":"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":"2307.01995","title":"Dynamic Feature-based Deep Reinforcement Learning for Flow Control of Circular Cylinder with Sparse Surface Pressure Sensing","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2310.17786","title":"Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2602.11767","title":"TSR: Trajectory-Search Rollouts for Multi-Turn RL of LLM Agents","created":"2026-02-12","cited_by_count":7,"area":"agents"},{"id":"2105.05145","title":"Visual Perspective Taking for Opponent Behavior Modeling","created":"2021-05-11","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":"2110.07985","title":"On-Policy Model Errors in Reinforcement Learning","created":"2021-10-15","cited_by_count":6,"area":null},{"id":"2112.01918","title":"Heuristic Search Planning with Deep Neural Networks using Imitation, Attention and Curriculum Learning","created":"2021-12-03","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":"2210.07636","title":"Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning","created":"2022-10-14","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":"2307.10936","title":"PASTA: Pretrained Action-State Transformer Agents","created":"2023-07-20","cited_by_count":6,"area":"agents"},{"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":"2412.04531","title":"MageBench: Bridging Large Multimodal Models to Agents","created":"2024-12-05","cited_by_count":6,"area":"mllm"},{"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":"2508.13113","title":"Contrastive Representations for Temporal Reasoning","created":"2025-08-18","cited_by_count":6,"area":"lr"},{"id":"2106.08272","title":"Deep Reinforcement Learning for Conservation Decisions","created":"2021-06-15","cited_by_count":5,"area":null},{"id":"2101.09933","title":"A Survey on Active Deep Learning: From Model-driven to Data-driven","created":"2021-01-25","cited_by_count":4,"area":null},{"id":"2105.01904","title":"Solving Sokoban with forward-backward reinforcement learning","created":"2021-05-05","cited_by_count":4,"area":null},{"id":"2206.01812","title":"Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks","created":"2022-06-03","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":"2506.10138","title":"Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN","created":"2025-06-11","cited_by_count":4,"area":"deeprl"},{"id":"2510.21995","title":"Is Temporal Difference Learning the Gold Standard for Stitching in RL?","created":"2025-10-24","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":"2104.03638","title":"Spatial Imagination With Semantic Cognition for Mobile Robots","created":"2021-04-08","cited_by_count":3,"area":null},{"id":"2206.14298","title":"Left Heavy Tails and the Effectiveness of the Policy and Value Networks in DNN-based best-first search for Sokoban Planning","created":"2022-06-28","cited_by_count":3,"area":null},{"id":"2305.14177","title":"ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2309.04615","title":"VDFD: Multi-Agent Value Decomposition Framework with Disentangled World Model","created":"2023-09-08","cited_by_count":3,"area":"wm"},{"id":"2311.10309","title":"Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments","created":"2023-11-17","cited_by_count":3,"area":"driving"},{"id":"2401.10516","title":"Episodic Reinforcement Learning with Expanded State-reward Space","created":"2024-01-19","cited_by_count":3,"area":"deeprl"},{"id":"2511.19528","title":"Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories","created":"2025-11-24","cited_by_count":3,"area":"vla"},{"id":"2602.00929","title":"Learning Abstractions for Hierarchical Planning in Program-Synthesis Agents","created":"2026-01-31","cited_by_count":3,"area":"agents"},{"id":"2607.03702","title":"Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry","created":"2026-07-04","cited_by_count":3,"area":"lr"},{"id":"2103.00446","title":"Learning for Visual Navigation by Imagining the Success","created":"2021-02-28","cited_by_count":2,"area":null},{"id":"2104.08196","title":"Towards Standardising Reinforcement Learning Approaches for Production Scheduling Problems","created":"2021-04-16","cited_by_count":2,"area":null},{"id":"2109.01768","title":"Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms","created":"2021-09-04","cited_by_count":2,"area":null},{"id":"2202.01461","title":"ExPoSe: Combining State-Based Exploration with Gradient-Based Online Search","created":"2022-02-03","cited_by_count":2,"area":null},{"id":"2209.02010","title":"On the Origins of Self-Modeling","created":"2022-09-05","cited_by_count":2,"area":null},{"id":"2209.05206","title":"A Differentiable Loss Function for Learning Heuristics in A*","created":"2022-09-12","cited_by_count":2,"area":null}],"next_cursor":"100"}