{"total":60,"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":"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":"2307.02484","title":"Elastic Decision Transformer","created":"2023-07-05","cited_by_count":67,"area":null},{"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":"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":"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":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"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":"2405.19586","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":"2308.09873","title":"Skill Transformer: A Monolithic Policy for Mobile Manipulation","created":"2023-08-19","cited_by_count":16,"area":null},{"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":"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":"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":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"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":"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":"2405.12262","title":"Prompt Learning for Generalized Vehicle Routing","created":"2024-05-20","cited_by_count":6,"area":null},{"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":"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":"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":"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":"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":"2505.00500","title":"Implicit Neural-Representation Learning for Elastic Deformable-Object Manipulations","created":"2025-05-01","cited_by_count":2,"area":null},{"id":"2507.06628","title":"Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2601.14523","title":"Large Language Model-Powered Evolutionary Code Optimization on a Phylogenetic Tree","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2601.20116","title":"In-Context Reinforcement Learning From Suboptimal Historical Data","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2604.13472","title":"Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2404.11144","title":"Self-adaptive PSRO: Towards an Automatic Population-based Game Solver","created":"2024-04-17","cited_by_count":1,"area":null},{"id":"2412.06877","title":"The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data","created":"2024-12-09","cited_by_count":1,"area":null},{"id":"2509.04535","title":"In-Context Policy Adaptation via Cross-Domain Skill Diffusion","created":"2025-09-04","cited_by_count":1,"area":null},{"id":"2609.36012","title":"In-Context Learning for Robots: Methods and Applications","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2405.12001","title":"Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning","created":"2024-05-20","cited_by_count":0,"area":null},{"id":"2406.16191","title":"Accelerating Matrix Diagonalization through Decision Transformers with Epsilon-Greedy Optimization","created":"2024-06-23","cited_by_count":0,"area":null},{"id":"2601.15912","title":"TeNet: Text-to-Network for Compact Policy Synthesis","created":"2026-01-22","cited_by_count":0,"area":null},{"id":"2605.29028","title":"Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2608.21858","title":"LLMs are Few-Shot Decision-Makers: Generalized Context-Aware Microgrid Frequency Control through Prompt Decision Transformer","created":"2026-08-22","cited_by_count":0,"area":null},{"id":"2609.17992","title":"The Operable Pareto Front: Distilling Offline Search into Run-Time Control for Multi-Objective UAV Edge-Computing Scheduling","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}