{"total":121,"rows":[{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175,"area":"offlinerl"},{"id":"2210.03370","title":"GNM: A General Navigation Model to Drive Any Robot","created":"2022-10-07","cited_by_count":171,"area":null},{"id":"2102.02202","title":"Embodied Intelligence via Learning and Evolution","created":"2021-02-03","cited_by_count":163,"area":null},{"id":"2402.17766","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","created":"2024-02-27","cited_by_count":137,"area":"mllm"},{"id":"2408.11812","title":"Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviation","created":"2024-08-21","cited_by_count":114,"area":null},{"id":"2203.11931","title":"MetaMorph: Learning Universal Controllers with Transformers","created":"2022-03-22","cited_by_count":89,"area":null},{"id":"2503.13441","title":"Humanoid Policy ~ Human Policy","created":"2025-03-17","cited_by_count":78,"area":null},{"id":"2201.04122","title":"In Defense of the Unitary Scalarization for Deep Multi-Task Learning","created":"2022-01-11","cited_by_count":67,"area":null},{"id":"2407.01531","title":"Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning","created":"2024-07-01","cited_by_count":57,"area":"diffusion"},{"id":"2509.04996","title":"FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policies","created":"2025-09-05","cited_by_count":57,"area":"vla"},{"id":"2209.05309","title":"GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots","created":"2022-09-12","cited_by_count":48,"area":null},{"id":"2409.06366","title":"One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion","created":"2024-09-10","cited_by_count":43,"area":"deeprl"},{"id":"2110.03659","title":"Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design","created":"2021-10-07","cited_by_count":38,"area":null},{"id":"2408.06316","title":"Body Transformer: Leveraging Robot Embodiment for Policy Learning","created":"2024-08-12","cited_by_count":32,"area":null},{"id":"2107.10847","title":"Accelerating Quadratic Optimization with Reinforcement Learning","created":"2021-07-22","cited_by_count":30,"area":null},{"id":"2206.07922","title":"Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications","created":"2022-06-16","cited_by_count":30,"area":null},{"id":"2206.12279","title":"AnyMorph: Learning Transferable Polices By Inferring Agent Morphology","created":"2022-06-17","cited_by_count":27,"area":null},{"id":"2207.07730","title":"How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2102.13100","title":"Task-Agnostic Morphology Evolution","created":"2021-02-25","cited_by_count":24,"area":null},{"id":"2305.10912","title":"A Generalist Dynamics Model for Control","created":"2023-05-18","cited_by_count":24,"area":"wm"},{"id":"2302.11070","title":"Universal Morphology Control via Contextual Modulation","created":"2023-02-22","cited_by_count":23,"area":null},{"id":"2103.03697","title":"Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms","created":"2021-03-05","cited_by_count":22,"area":null},{"id":"2105.10049","title":"Learning Modular Robot Control Policies","created":"2021-05-20","cited_by_count":22,"area":null},{"id":"2203.13733","title":"Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning","created":"2022-03-15","cited_by_count":22,"area":null},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21,"area":null},{"id":"2303.03747","title":"Graph Decision Transformer","created":"2023-03-07","cited_by_count":20,"area":"offlinerl"},{"id":"2509.23745","title":"LocoFormer: Generalist Locomotion via Long-context Adaptation","created":"2025-09-28","cited_by_count":20,"area":null},{"id":"2310.10486","title":"ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robots","created":"2023-10-16","cited_by_count":19,"area":null},{"id":"2602.10556","title":"LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer","created":"2026-02-11","cited_by_count":18,"area":"vla"},{"id":"2110.09461","title":"In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications","created":"2021-10-18","cited_by_count":17,"area":null},{"id":"2209.11748","title":"GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automation","created":"2022-09-23","cited_by_count":16,"area":null},{"id":"2210.15479","title":"Low-Rank Modular Reinforcement Learning via Muscle Synergy","created":"2022-10-26","cited_by_count":16,"area":null},{"id":"2505.05753","title":"Towards Embodiment Scaling Laws in Robot Locomotion","created":"2025-05-09","cited_by_count":16,"area":null},{"id":"2203.04482","title":"Multi-Agent Policy Transfer via Task Relationship Modeling","created":"2022-03-09","cited_by_count":14,"area":null},{"id":"2205.13005","title":"QGNN: Value Function Factorisation with Graph Neural Networks","created":"2022-05-25","cited_by_count":14,"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":"2211.14296","title":"A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation","created":"2022-11-25","cited_by_count":13,"area":null},{"id":"2306.00036","title":"Symmetry-Aware Robot Design with Structured Subgroups","created":"2023-05-31","cited_by_count":13,"area":null},{"id":"2210.05448","title":"A General Learning Framework for Open Ad Hoc Teamwork Using Graph-based Policy Learning","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2309.02435","title":"Efficient RL via Disentangled Environment and Agent Representations","created":"2023-09-05","cited_by_count":12,"area":null},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2305.18951","title":"Subequivariant Graph Reinforcement Learning in 3D Environments","created":"2023-05-30","cited_by_count":11,"area":null},{"id":"2401.03244","title":"Artificial Intelligence for Operations Research: Revolutionizing the Operations Research Process","created":"2024-01-06","cited_by_count":11,"area":null},{"id":"2402.06570","title":"Distilling Morphology-Conditioned Hypernetworks for Efficient Universal Morphology Control","created":"2024-02-09","cited_by_count":11,"area":null},{"id":"2410.17647","title":"Entity-based Reinforcement Learning for Autonomous Cyber Defence","created":"2024-10-23","cited_by_count":11,"area":"deeprl"},{"id":"2510.02614","title":"UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies","created":"2025-10-02","cited_by_count":11,"area":"diffusion"},{"id":"2502.07005","title":"Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects","created":"2025-02-10","cited_by_count":10,"area":null},{"id":"2512.13100","title":"OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning","created":"2025-12-15","cited_by_count":10,"area":"vla"},{"id":"2301.10497","title":"E(n)-equivariant Graph Neural Cellular Automata","created":"2023-01-25","cited_by_count":9,"area":null},{"id":"2503.00533","title":"BodyGen: Advancing Towards Efficient Embodiment Co-Design","created":"2025-03-01","cited_by_count":9,"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":"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":"2301.12305","title":"Composing Task Knowledge with Modular Successor Feature Approximators","created":"2023-01-28","cited_by_count":7,"area":null},{"id":"2505.15211","title":"GCNT: Graph-Based Transformer Policies for Morphology-Agnostic Reinforcement Learning","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2506.06376","title":"Enhancing Decision-Making of Large Language Models via Actor-Critic","created":"2025-06-04","cited_by_count":7,"area":null},{"id":"2209.14218","title":"DMAP: a Distributed Morphological Attention Policy for Learning to Locomote with a Changing Body","created":"2022-09-28","cited_by_count":6,"area":null},{"id":"2407.00633","title":"DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction","created":"2024-06-30","cited_by_count":6,"area":"deeprl"},{"id":"2502.10862","title":"Accelerated co-design of robots through morphological pretraining","created":"2025-02-15","cited_by_count":6,"area":"deeprl"},{"id":"2104.12365","title":"Efficient Hyperparameter Optimization for Physics-based Character Animation","created":"2021-04-26","cited_by_count":5,"area":null},{"id":"2310.00871","title":"COMPOSER: Scalable and Robust Modular Policies for Snake Robots","created":"2023-10-02","cited_by_count":5,"area":null},{"id":"2311.00462","title":"Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design","created":"2023-11-01","cited_by_count":5,"area":null},{"id":"2403.02018","title":"Cross Domain Policy Transfer with Effect Cycle-Consistency","created":"2024-03-04","cited_by_count":5,"area":"deeprl"},{"id":"2408.05686","title":"The Bandit Whisperer: Communication Learning for Restless Bandits","created":"2024-08-11","cited_by_count":5,"area":null},{"id":"2505.18780","title":"DreamPolicy: A Unified World-model Policy for Scalable Humanoid Locomotion","created":"2025-05-24","cited_by_count":5,"area":"wm"},{"id":"2508.07842","title":"DETACH: Cross-domain Learning for Long-Horizon Tasks via Mixture of Disentangled Experts","created":"2025-08-11","cited_by_count":5,"area":null},{"id":"2512.03743","title":"House of Dextra: Cross-embodied Co-design for Dexterous Hands","created":"2025-12-03","cited_by_count":5,"area":null},{"id":"2302.13191","title":"DeepCPG Policies for Robot Locomotion","created":"2023-02-25","cited_by_count":4,"area":null},{"id":"2304.05099","title":"Feudal Graph Reinforcement Learning","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2306.17411","title":"Decentralized Motor Skill Learning for Complex Robotic Systems","created":"2023-06-30","cited_by_count":4,"area":null},{"id":"2407.05789","title":"CANDID DAC: Leveraging Coupled Action Dimensions with Importance Differences in DAC","created":"2024-07-08","cited_by_count":4,"area":null},{"id":"2408.01230","title":"HeteroMorpheus: Universal Control Based on Morphological Heterogeneity Modeling","created":"2024-08-02","cited_by_count":4,"area":null},{"id":"2412.12147","title":"Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control","created":"2024-12-10","cited_by_count":4,"area":null},{"id":"2502.01366","title":"Trajectory World Models for Heterogeneous Environments","created":"2025-02-03","cited_by_count":4,"area":"wm"},{"id":"2512.00727","title":"Beyond Topology: A Morphological Symmetry Graph Representation for Locomotion Policy Learning","created":"2025-11-30","cited_by_count":4,"area":"deeprl"},{"id":"2512.04770","title":"Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges","created":"2025-12-04","cited_by_count":4,"area":null},{"id":"2604.08780","title":"Morphology-Conditioned World Model for Cross-Embodiment Quadrupedal Locomotion","created":"2026-04-09","cited_by_count":4,"area":"wm"},{"id":"2204.02099","title":"Collective control of modular soft robots via embodied Spiking Neural Cellular Automata","created":"2022-04-05","cited_by_count":3,"area":null},{"id":"2306.13554","title":"Comparing the Efficacy of Fine-Tuning and Meta-Learning for Few-Shot Policy Imitation","created":"2023-06-23","cited_by_count":3,"area":"offlinerl"},{"id":"2405.03534","title":"Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer","created":"2024-05-06","cited_by_count":3,"area":null},{"id":"2504.06523","title":"Controller Distillation Reduces Fragile Brain-Body Co-Adaptation and Enables Migrations in MAP-Elites","created":"2025-04-09","cited_by_count":3,"area":null},{"id":"2505.20857","title":"Multi-Embodiment Robotic Retargeting via Guided Diffusion Model","created":"2025-05-27","cited_by_count":3,"area":"diffusion"},{"id":"2506.08630","title":"Shared Modular Recurrence in Contextual MDPs for Universal Morphology Control","created":"2025-06-10","cited_by_count":3,"area":null},{"id":"2603.00182","title":"Embedding Morphology into Transformers for Cross-Robot Policy Learning","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2111.02371","title":"What Robot do I Need? Fast Co-Adaptation of Morphology and Control using Graph Neural Networks","created":"2021-11-03","cited_by_count":2,"area":null},{"id":"2211.15136","title":"Collective Intelligence for 2D Push Manipulations with Mobile Robots","created":"2022-11-28","cited_by_count":2,"area":null},{"id":"2404.14625","title":"Towards Multi-Morphology Controllers with Diversity and Knowledge Distillation","created":"2024-04-22","cited_by_count":2,"area":"distill"},{"id":"2406.07837","title":"Scaling Manipulation Learning with Visual Kinematic Chain Prediction","created":"2024-06-12","cited_by_count":2,"area":null},{"id":"2407.12505","title":"Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments","created":"2024-07-17","cited_by_count":2,"area":"deeprl"},{"id":"2412.04273","title":"Reinforcement Learning from Wild Animal Videos","created":"2024-12-05","cited_by_count":2,"area":"deeprl"},{"id":"2510.22336","title":"Toward Humanoid Brain-Body Co-design: Joint Optimization of Control and Morphology for Fall Recovery","created":"2025-10-25","cited_by_count":2,"area":null},{"id":"2606.00702","title":"Shape Your Body: Value Gradients for Multi-Embodiment Robot Design","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2606.24208","title":"Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control","created":"2026-06-23","cited_by_count":2,"area":"diffusion"},{"id":"2112.07222","title":"Meta-CPR: Generalize to Unseen Large Number of Agents with Communication Pattern Recognition Module","created":"2021-12-14","cited_by_count":1,"area":null},{"id":"2211.08234","title":"Build generally reusable agent-environment interaction models","created":"2022-11-13","cited_by_count":1,"area":null},{"id":"2407.01567","title":"MeMo: Meaningful, Modular Controllers via Noise Injection","created":"2024-05-24","cited_by_count":1,"area":null},{"id":"2407.17502","title":"MetaLoco: Universal Quadrupedal Locomotion with Meta-Reinforcement Learning and Motion Imitation","created":"2024-07-05","cited_by_count":1,"area":"deeprl"},{"id":"2505.18418","title":"McARL:Morphology-Control-Aware Reinforcement Learning for Generalizable Quadrupedal Locomotion","created":"2025-05-23","cited_by_count":1,"area":"deeprl"}],"next_cursor":"100"}