{"total":146,"rows":[{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407,"area":null},{"id":"2307.04721","title":"Large Language Models as General Pattern Machines","created":"2023-07-10","cited_by_count":197,"area":null},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190,"area":null},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2305.18459","title":"Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning","created":"2023-05-29","cited_by_count":115,"area":"diffusion"},{"id":"2411.04549","title":"Vision Language Models are In-Context Value Learners","created":"2024-11-07","cited_by_count":90,"area":"mllm"},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86,"area":null},{"id":"2403.15371","title":"Can large language models explore in-context?","created":"2024-03-22","cited_by_count":76,"area":null},{"id":"2312.11598","title":"SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution","created":"2023-12-18","cited_by_count":70,"area":"diffusion"},{"id":"2408.15980","title":"In-Context Imitation Learning via Next-Token Prediction","created":"2024-08-28","cited_by_count":70,"area":"offlinerl"},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2305.19923","title":"MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL","created":"2023-05-31","cited_by_count":68,"area":"diffusion"},{"id":"2307.02484","title":"Elastic Decision Transformer","created":"2023-07-05","cited_by_count":67,"area":null},{"id":"2310.05905","title":"TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models","created":"2023-10-09","cited_by_count":53,"area":"offlinerl"},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"area":null},{"id":"2312.03801","title":"Generalization to New Sequential Decision Making Tasks with In-Context Learning","created":"2023-12-06","cited_by_count":39,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2305.18882","title":"What is Essential for Unseen Goal Generalization of Offline Goal-conditioned RL?","created":"2023-05-30","cited_by_count":36,"area":"offlinerl"},{"id":"2304.08487","title":"Hyper-Decision Transformer for Efficient Online Policy Adaptation","created":"2023-04-17","cited_by_count":33,"area":"offlinerl"},{"id":"2412.01441","title":"LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations","created":"2024-12-02","cited_by_count":32,"area":"offlinerl"},{"id":"2210.03821","title":"Large Language Models can Implement Policy Iteration","created":"2022-10-07","cited_by_count":31,"area":null},{"id":"2410.05362","title":"LLMs Are In-Context Bandit Reinforcement Learners","created":"2024-10-07","cited_by_count":29,"area":null},{"id":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28,"area":null},{"id":"2310.03022","title":"Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making","created":"2023-10-04","cited_by_count":26,"area":"offlinerl"},{"id":"2310.20587","title":"Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning","created":"2023-10-31","cited_by_count":24,"area":"offlinerl"},{"id":"2312.13327","title":"In-Context Reinforcement Learning for Variable Action Spaces","created":"2023-12-20","cited_by_count":24,"area":null},{"id":"2209.13020","title":"Law Informs Code: A Legal Informatics Approach to Aligning Artificial Intelligence with Humans","created":"2022-09-14","cited_by_count":23,"area":null},{"id":"2306.14069","title":"Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets","created":"2023-06-24","cited_by_count":22,"area":"offlinerl"},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2402.13777","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","created":"2024-02-21","cited_by_count":20,"area":"offlinerl"},{"id":"2305.09648","title":"Prompt-Tuning Decision Transformer with Preference Ranking","created":"2023-05-16","cited_by_count":19,"area":null},{"id":"2306.13945","title":"Large Sequence Models for Sequential Decision-Making: A Survey","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2405.13178","title":"One-Shot Imitation Learning with Invariance Matching for Robotic Manipulation","created":"2024-05-21","cited_by_count":18,"area":"offlinerl"},{"id":"2405.19586","title":"SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation","created":"2024-05-30","cited_by_count":18,"area":null},{"id":"2501.13896","title":"GUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Exploration","created":"2025-01-23","cited_by_count":18,"area":null},{"id":"2402.02429","title":"Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning","created":"2024-02-04","cited_by_count":17,"area":"offlinerl"},{"id":"2410.11448","title":"Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement","created":"2024-10-15","cited_by_count":17,"area":"wm"},{"id":"2301.12203","title":"SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning","created":"2023-01-28","cited_by_count":16,"area":"offlinerl"},{"id":"2308.09873","title":"Skill Transformer: A Monolithic Policy for Mobile Manipulation","created":"2023-08-19","cited_by_count":16,"area":null},{"id":"2412.04759","title":"REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments","created":"2024-12-06","cited_by_count":16,"area":"rag"},{"id":"2207.02442","title":"Transformers are Adaptable Task Planners","created":"2022-07-06","cited_by_count":15,"area":null},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2505.24378","title":"Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer","created":"2025-05-30","cited_by_count":15,"area":"moe"},{"id":"2302.08102","title":"Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition","created":"2023-02-16","cited_by_count":14,"area":null},{"id":"2311.00267","title":"Rethinking Decision Transformer via Hierarchical Reinforcement Learning","created":"2023-11-01","cited_by_count":14,"area":"offlinerl"},{"id":"2405.18080","title":"HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning","created":"2024-05-28","cited_by_count":14,"area":"offlinerl"},{"id":"2410.00564","title":"Scaling Offline Model-Based RL via Jointly-Optimized World-Action Model Pretraining","created":"2024-10-01","cited_by_count":14,"area":"wm"},{"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":"2306.14534","title":"CEIL: Generalized Contextual Imitation Learning","created":"2023-06-26","cited_by_count":13,"area":"offlinerl"},{"id":"2410.23450","title":"Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning","created":"2024-10-30","cited_by_count":13,"area":"offlinerl"},{"id":"2306.08204","title":"Unraveling the ARC Puzzle: Mimicking Human Solutions with Object-Centric Decision Transformer","created":"2023-06-14","cited_by_count":12,"area":"offlinerl"},{"id":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2303.03391","title":"Decision Transformer under Random Frame Dropping","created":"2023-03-03","cited_by_count":10,"area":"offlinerl"},{"id":"2404.12090","title":"X-Light: Cross-City Traffic Signal Control Using Transformer on Transformer as Meta Multi-Agent Reinforcement Learner","created":"2024-04-18","cited_by_count":10,"area":null},{"id":"2410.20357","title":"Dynamics as Prompts: In-Context Learning for Sim-to-Real System Identifications","created":"2024-10-27","cited_by_count":10,"area":null},{"id":"2405.17009","title":"Position: Foundation Agents as the Paradigm Shift for Decision Making","created":"2024-05-27","cited_by_count":9,"area":"agents"},{"id":"2208.01220","title":"GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction","created":"2022-08-02","cited_by_count":8,"area":null},{"id":"2312.11442","title":"Explore 3D Dance Generation via Reward Model from Automatically-Ranked Demonstrations","created":"2023-12-18","cited_by_count":8,"area":null},{"id":"2502.00225","title":"Should You Use Your Large Language Model to Explore or Exploit?","created":"2025-01-31","cited_by_count":8,"area":null},{"id":"2506.05426","title":"Mixture-of-Experts Meets In-Context Reinforcement Learning","created":"2025-06-05","cited_by_count":8,"area":"moe"},{"id":"2210.15906","title":"Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences","created":"2022-10-28","cited_by_count":7,"area":"alignment"},{"id":"2211.08016","title":"Contextual Transformer for Offline Meta Reinforcement Learning","created":"2022-11-15","cited_by_count":7,"area":"offlinerl"},{"id":"2407.00898","title":"Residual-MPPI: Online Policy Customization for Continuous Control","created":"2024-07-01","cited_by_count":7,"area":"offlinerl"},{"id":"2407.04285","title":"Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling","created":"2024-07-05","cited_by_count":7,"area":"offlinerl"},{"id":"2502.05397","title":"Imitation Learning from a Single Temporally Misaligned Video","created":"2025-02-08","cited_by_count":7,"area":"offlinerl"},{"id":"2401.08478","title":"Solving Continual Offline Reinforcement Learning with Decision Transformer","created":"2024-01-16","cited_by_count":6,"area":"offlinerl"},{"id":"2405.12262","title":"Prompt Learning for Generalized Vehicle Routing","created":"2024-05-20","cited_by_count":6,"area":null},{"id":"2408.01402","title":"Pre-trained Language Models Improve the Few-shot Prompt Ability of Decision Transformer","created":"2024-08-02","cited_by_count":6,"area":"offlinerl"},{"id":"2410.03408","title":"Predictive Coding for Decision Transformer","created":"2024-10-04","cited_by_count":6,"area":"offlinerl"},{"id":"2411.01168","title":"Prompt Tuning with Diffusion for Few-Shot Pre-trained Policy Generalization","created":"2024-11-02","cited_by_count":6,"area":"offlinerl"},{"id":"2411.01789","title":"Generating executable oracles to check conformance of client code to requirements of JDK Javadocs using LLMs","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2303.01668","title":"RePreM: Representation Pre-training with Masked Model for Reinforcement Learning","created":"2023-03-03","cited_by_count":5,"area":null},{"id":"2404.02407","title":"Decision Transformer as a Foundation Model for Partially Observable Continuous Control","created":"2024-04-03","cited_by_count":5,"area":"offlinerl"},{"id":"2409.09958","title":"An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning","created":"2024-09-16","cited_by_count":5,"area":"deeprl"},{"id":"2502.05187","title":"An Adaptable Budget Planner for Enhancing Budget-Constrained Auto-Bidding in Online Advertising","created":"2025-01-26","cited_by_count":5,"area":null},{"id":"2504.15046","title":"Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision","created":"2025-04-21","cited_by_count":5,"area":"offlinerl"},{"id":"2508.06659","title":"In-Context Reinforcement Learning via Communicative World Models","created":"2025-08-08","cited_by_count":5,"area":"wm"},{"id":"2509.19658","title":"RoboSSM: Scalable In-context Imitation Learning via State-Space Models","created":"2025-09-24","cited_by_count":5,"area":"offlinerl"},{"id":"2407.18414","title":"Adversarially Robust Decision Transformer","created":"2024-07-25","cited_by_count":4,"area":"offlinerl"},{"id":"2411.04987","title":"Few-Shot Task Learning through Inverse Generative Modeling","created":"2024-11-07","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":"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":"2401.16452","title":"Context-Former: Stitching via Latent Conditioned Sequence Modeling","created":"2024-01-29","cited_by_count":3,"area":"offlinerl"},{"id":"2405.18729","title":"Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning","created":"2024-05-29","cited_by_count":3,"area":"diffusion"},{"id":"2406.18505","title":"Mental Modeling of Reinforcement Learning Agents by Language Models","created":"2024-06-26","cited_by_count":3,"area":"agents"},{"id":"2409.06985","title":"Unveiling Markov Heads in Pretrained Language Models for Offline Reinforcement Learning","created":"2024-09-11","cited_by_count":3,"area":"offlinerl"},{"id":"2412.00979","title":"Hierarchical Prompt Decision Transformer: Improving Few-Shot Policy Generalization with Global and Adaptive Guidance","created":"2024-12-01","cited_by_count":3,"area":"offlinerl"},{"id":"2509.25582","title":"Safe In-Context Reinforcement Learning","created":"2025-09-29","cited_by_count":3,"area":"deeprl"},{"id":"2210.07658","title":"Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization","created":"2022-10-14","cited_by_count":2,"area":null},{"id":"2401.00031","title":"Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges","created":"2023-12-29","cited_by_count":2,"area":null},{"id":"2402.07418","title":"SemTra: A Semantic Skill Translator for Cross-Domain Zero-Shot Policy Adaptation","created":"2024-02-12","cited_by_count":2,"area":null},{"id":"2402.09729","title":"Federated Prompt-based Decision Transformer for Customized VR Services in Mobile Edge Computing System","created":"2024-02-15","cited_by_count":2,"area":null},{"id":"2402.11317","title":"Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics","created":"2024-02-17","cited_by_count":2,"area":"deeprl"},{"id":"2403.07261","title":"Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation","created":"2024-03-12","cited_by_count":2,"area":"offlinerl"},{"id":"2405.06063","title":"A Minimalist Prompt for Zero-Shot Policy Learning","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2407.19380","title":"Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment","created":"2024-07-28","cited_by_count":2,"area":null},{"id":"2409.02512","title":"Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal","created":"2024-09-04","cited_by_count":2,"area":"offlinerl"},{"id":"2410.19982","title":"Random Policy Enables In-Context Reinforcement Learning within Trust Horizons","created":"2024-10-25","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}