{"total":12,"rows":[{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139,"area":null},{"id":"2307.02484","title":"Elastic Decision Transformer","created":"2023-07-05","cited_by_count":67,"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":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28,"area":null},{"id":"2403.11558","title":"Reinforcement Learning with Token-level Feedback for Controllable Text Generation","created":"2024-03-18","cited_by_count":16,"area":null},{"id":"2407.10973","title":"Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion","created":"2024-07-15","cited_by_count":14,"area":null},{"id":"2402.06187","title":"Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss","created":"2024-02-09","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":"2506.05985","title":"Dynamic Mixture of Progressive Parameter-Efficient Expert Library for Lifelong Robot Learning","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2405.03924","title":"NeurDB: An AI-powered Autonomous Data System","created":"2024-05-07","cited_by_count":5,"area":null},{"id":"2309.16663","title":"HyperPPO: A scalable method for finding small policies for robotic control","created":"2023-09-28","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}],"next_cursor":null}