{"total":127,"rows":[{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458,"area":"wm"},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105,"area":null},{"id":"2504.20995","title":"TesserAct: Learning 4D Embodied World Models","created":"2025-04-29","cited_by_count":94,"area":"wm"},{"id":"2502.14819","title":"Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models","created":"2025-02-20","cited_by_count":89,"area":null},{"id":"2101.07241","title":"Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos","created":"2021-01-18","cited_by_count":87,"area":null},{"id":"2206.04779","title":"Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations","created":"2022-06-09","cited_by_count":63,"area":"offlinerl"},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2408.14472","title":"Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning","created":"2024-08-26","cited_by_count":56,"area":"wm"},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2206.01634","title":"Reinforcement Learning with Neural Radiance Fields","created":"2022-06-03","cited_by_count":43,"area":null},{"id":"2103.04351","title":"Learning a State Representation and Navigation in Cluttered and Dynamic Environments","created":"2021-03-07","cited_by_count":41,"area":null},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2306.09643","title":"BISCUIT: Causal Representation Learning from Binary Interactions","created":"2023-06-16","cited_by_count":38,"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":"2105.12272","title":"Provable Representation Learning for Imitation with Contrastive Fourier Features","created":"2021-05-26","cited_by_count":34,"area":"offlinerl"},{"id":"2101.02055","title":"Geometric Entropic Exploration","created":"2021-01-06","cited_by_count":32,"area":null},{"id":"2110.05721","title":"Action-Sufficient State Representation Learning for Control with Structural Constraints","created":"2021-10-12","cited_by_count":31,"area":null},{"id":"2106.07278","title":"Which Mutual-Information Representation Learning Objectives are Sufficient for Control?","created":"2021-06-14","cited_by_count":29,"area":null},{"id":"2112.04907","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","created":"2021-12-07","cited_by_count":28,"area":"offlinerl"},{"id":"2407.13237","title":"LLM-Empowered State Representation for Reinforcement Learning","created":"2024-07-18","cited_by_count":28,"area":null},{"id":"2602.02454","title":"World-Gymnast: Training Robots with Reinforcement Learning in a World Model","created":"2026-02-02","cited_by_count":27,"area":"wm"},{"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":"2106.06098","title":"Meta-Adaptive Nonlinear Control: Theory and Algorithms","created":"2021-06-11","cited_by_count":23,"area":null},{"id":"2103.04412","title":"Multimodal VAE Active Inference Controller","created":"2021-03-07","cited_by_count":21,"area":null},{"id":"2207.08673","title":"Back to the Manifold: Recovering from Out-of-Distribution States","created":"2022-07-18","cited_by_count":20,"area":null},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2302.12232","title":"Concept Learning for Interpretable Multi-Agent Reinforcement Learning","created":"2023-02-23","cited_by_count":19,"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":"2309.00082","title":"RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability","created":"2023-08-31","cited_by_count":18,"area":null},{"id":"2106.01834","title":"Continual Learning in Deep Networks: an Analysis of the Last Layer","created":"2021-06-03","cited_by_count":17,"area":null},{"id":"2203.11203","title":"Reinforcement learning for automatic quadrilateral mesh generation: a soft actor-critic approach","created":"2022-03-19","cited_by_count":17,"area":null},{"id":"2506.17518","title":"A Survey of State Representation Learning for Deep Reinforcement Learning","created":"2025-06-20","cited_by_count":17,"area":"deeprl"},{"id":"2105.02658","title":"Explainable Autonomous Robots: A Survey and Perspective","created":"2021-05-06","cited_by_count":15,"area":null},{"id":"2503.23616","title":"Interpretable Machine Learning in Physics: A Review","created":"2025-03-30","cited_by_count":14,"area":null},{"id":"2305.12751","title":"Testing of Deep Reinforcement Learning Agents with Surrogate Models","created":"2023-05-22","cited_by_count":13,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2107.01667","title":"Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spaces","created":"2021-07-04","cited_by_count":9,"area":null},{"id":"2110.12603","title":"Common Information based Approximate State Representations in Multi-Agent Reinforcement Learning","created":"2021-10-25","cited_by_count":8,"area":null},{"id":"2304.11052","title":"A Multiagent CyberBattleSim for RL Cyber Operation Agents","created":"2023-04-03","cited_by_count":8,"area":null},{"id":"2608.22764","title":"LpWM: A Case for Sparse Representations in World Models","created":"2026-08-24","cited_by_count":8,"area":"wm"},{"id":"2001.11628","title":"Domain-Adversarial and Conditional State Space Model for Imitation Learning","created":"2020-01-31","cited_by_count":7,"area":"offlinerl"},{"id":"2403.15267","title":"Parametric PDE Control with Deep Reinforcement Learning and Differentiable L0-Sparse Polynomial Policies","created":"2024-03-22","cited_by_count":7,"area":"deeprl"},{"id":"2006.11309","title":"Modelling Agent Policies with Interpretable Imitation Learning","created":"2020-06-19","cited_by_count":6,"area":"offlinerl"},{"id":"2110.03608","title":"How to Sense the World: Leveraging Hierarchy in Multimodal Perception for Robust Reinforcement Learning Agents","created":"2021-10-07","cited_by_count":6,"area":null},{"id":"2112.06752","title":"Adaptation through prediction: multisensory active inference torque control","created":"2021-12-13","cited_by_count":6,"area":null},{"id":"2202.05333","title":"Factored World Models for Zero-Shot Generalization in Robotic Manipulation","created":"2022-02-10","cited_by_count":6,"area":"wm"},{"id":"2208.12975","title":"Deep Kernel Learning of Dynamical Models from High-Dimensional Noisy Data","created":"2022-08-27","cited_by_count":6,"area":null},{"id":"2508.20840","title":"Learning Primitive Embodied World Models: Towards Scalable Robotic Learning","created":"2025-08-28","cited_by_count":6,"area":"wm"},{"id":"1910.01738","title":"State Representation Learning from Demonstration","created":"2019-09-15","cited_by_count":5,"area":"offlinerl"},{"id":"2110.11573","title":"A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving","created":"2021-10-22","cited_by_count":5,"area":"driving"},{"id":"2208.14928","title":"Cell-Free Latent Go-Explore","created":"2022-08-31","cited_by_count":5,"area":null},{"id":"2510.14129","title":"Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL","created":"2025-10-15","cited_by_count":5,"area":"deeprl"},{"id":"2510.21609","title":"Enhancing Tactile-based Reinforcement Learning for Robotic Control","created":"2025-10-24","cited_by_count":5,"area":"deeprl"},{"id":"2203.08715","title":"Multiscale Sensor Fusion and Continuous Control with Neural CDEs","created":"2022-03-16","cited_by_count":4,"area":null},{"id":"2212.13088","title":"Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities","created":"2022-12-26","cited_by_count":4,"area":null},{"id":"2410.17551","title":"Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensors","created":"2024-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2503.08306","title":"Reasoning in visual navigation of end-to-end trained agents: a dynamical systems approach","created":"2025-03-11","cited_by_count":4,"area":null},{"id":"2506.22365","title":"Reinforcement Learning with Physics-Informed Symbolic Program Priors for Zero-Shot Wireless Indoor Navigation","created":"2025-06-27","cited_by_count":4,"area":"deeprl"},{"id":"2603.20048","title":"Structured Latent Dynamics in Wireless CSI via Homomorphic World Models","created":"2026-03-20","cited_by_count":4,"area":"wm"},{"id":"2110.12352","title":"DiffSRL: Learning Dynamical State Representation for Deformable Object Manipulation with Differentiable Simulator","created":"2021-10-24","cited_by_count":3,"area":null},{"id":"2305.10267","title":"State Representation Learning Using an Unbalanced Atlas","created":"2023-05-17","cited_by_count":3,"area":null},{"id":"2401.11512","title":"TERC: A Transfer Entropy Redundancy Criterion for State Variable Selection in Reinforcement Learning","created":"2024-01-21","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":"2407.11069","title":"Combining Federated Learning and Control: A Survey","created":"2024-07-12","cited_by_count":3,"area":null},{"id":"2410.14038","title":"Sliding Puzzles Gym: A Scalable Benchmark for State Representation in Visual Reinforcement Learning","created":"2024-10-17","cited_by_count":3,"area":"deeprl"},{"id":"2501.04538","title":"HypeRL: Hypernetwork-Based Reinforcement Learning for Control of Parametrized Dynamical Systems","created":"2025-01-08","cited_by_count":3,"area":"deeprl"},{"id":"2510.02287","title":"MultiModal Action Conditioned Video Generation","created":"2025-10-02","cited_by_count":3,"area":"wm"},{"id":"2105.06660","title":"Estimating Disentangled Belief about Hidden State and Hidden Task for Meta-RL","created":"2021-05-14","cited_by_count":2,"area":null},{"id":"2107.01677","title":"Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metrics","created":"2021-07-04","cited_by_count":2,"area":null},{"id":"2109.13596","title":"Exploratory State Representation Learning","created":"2021-09-28","cited_by_count":2,"area":null},{"id":"2110.00784","title":"Seeking Visual Discomfort: Curiosity-driven Representations for Reinforcement Learning","created":"2021-10-02","cited_by_count":2,"area":null},{"id":"2205.08712","title":"CARNet: A Dynamic Autoencoder for Learning Latent Dynamics in Autonomous Driving Tasks","created":"2022-05-18","cited_by_count":2,"area":"driving"},{"id":"2212.01744","title":"Statistical Physics of Deep Neural Networks: Initialization toward Optimal Channels","created":"2022-12-04","cited_by_count":2,"area":null},{"id":"2302.11563","title":"Self-supervised network distillation: an effective approach to exploration in sparse reward environments","created":"2023-02-22","cited_by_count":2,"area":null},{"id":"2305.14644","title":"KARNet: Kalman Filter Augmented Recurrent Neural Network for Learning World Models in Autonomous Driving Tasks","created":"2023-05-24","cited_by_count":2,"area":"wm"},{"id":"2310.01536","title":"Algebras of actions in an agent's representations of the world","created":"2023-10-02","cited_by_count":2,"area":null},{"id":"2408.00343","title":"IN-Sight: Interactive Navigation through Sight","created":"2024-08-01","cited_by_count":2,"area":null},{"id":"2408.14685","title":"Model-Based Reinforcement Learning for Control of Strongly-Disturbed Unsteady Aerodynamic Flows","created":"2024-08-26","cited_by_count":2,"area":"deeprl"},{"id":"2411.04098","title":"Interpretable and Efficient Data-driven Discovery and Control of Distributed Systems","created":"2024-11-06","cited_by_count":2,"area":"deeprl"},{"id":"2502.02327","title":"Policy-Guided Causal State Representation for Offline Reinforcement Learning Recommendation","created":"2025-02-04","cited_by_count":2,"area":"offlinerl"},{"id":"2101.01774","title":"An A* Curriculum Approach to Reinforcement Learning for RGBD Indoor Robot Navigation","created":"2021-01-05","cited_by_count":1,"area":null},{"id":"2103.08137","title":"Cloth Manipulation Planning on Basis of Mesh Representations with Incomplete Domain Knowledge and Voxel-to-Mesh Estimation","created":"2021-03-15","cited_by_count":1,"area":null},{"id":"2208.03936","title":"Sparse Representation Learning with Modified q-VAE towards Minimal Realization of World Model","created":"2022-08-08","cited_by_count":1,"area":"wm"},{"id":"2210.02224","title":"Neural Distillation as a State Representation Bottleneck in Reinforcement Learning","created":"2022-10-05","cited_by_count":1,"area":null},{"id":"2303.04218","title":"Deep Occupancy-Predictive Representations for Autonomous Driving","created":"2023-03-07","cited_by_count":1,"area":"driving"},{"id":"2307.11408","title":"Direct and inverse modeling of soft robots by learning a condensed FEM model","created":"2023-07-21","cited_by_count":1,"area":null},{"id":"2309.11984","title":"State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2310.04241","title":"Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison","created":"2023-10-06","cited_by_count":1,"area":null},{"id":"2407.13091","title":"On Causally Disentangled State Representation Learning for Reinforcement Learning based Recommender Systems","created":"2024-07-18","cited_by_count":1,"area":"deeprl"},{"id":"2508.07452","title":"Stackelberg Coupling of Online Representation Learning and Reinforcement Learning","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2509.11880","title":"Learning Representations in Video Game Agents with Supervised Contrastive Imitation Learning","created":"2025-09-15","cited_by_count":1,"area":"offlinerl"},{"id":"2603.01748","title":"Discrete World Models via Regularization","created":"2026-03-02","cited_by_count":1,"area":"wm"},{"id":"2605.11711","title":"Debiased Model-based Representations for Sample-efficient Continuous Control","created":"2026-05-12","cited_by_count":1,"area":"deeprl"},{"id":"2107.13109","title":"Pixyz: a Python library for developing deep generative models","created":"2021-07-28","cited_by_count":0,"area":null},{"id":"2109.08642","title":"POAR: Efficient Policy Optimization via Online Abstract State Representation Learning","created":"2021-09-17","cited_by_count":0,"area":null},{"id":"2201.07051","title":"System-Agnostic Meta-Learning for MDP-based Dynamic Scheduling via Descriptive Policy","created":"2022-01-18","cited_by_count":0,"area":null},{"id":"2206.06712","title":"Visual Radial Basis Q-Network","created":"2022-06-14","cited_by_count":0,"area":null},{"id":"2208.12627","title":"Symbolic Explanation of Affinity-Based Reinforcement Learning Agents with Markov Models","created":"2022-08-26","cited_by_count":0,"area":null}],"next_cursor":"100"}