{"total":23,"rows":[{"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":"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":"2312.12275","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","created":"2023-12-19","cited_by_count":27,"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":"2402.04647","title":"Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference","created":"2024-02-07","cited_by_count":14,"area":null},{"id":"2310.19308","title":"Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning","created":"2023-10-30","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":"2510.26389","title":"Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2510.16457","title":"NavQ: Learning a Q-Model for Foresighted Vision-and-Language Navigation","created":"2025-10-18","cited_by_count":6,"area":null},{"id":"2408.10286","title":"GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching","created":"2024-08-19","cited_by_count":5,"area":null},{"id":"2603.11099","title":"Graph Tokenization for Bridging Graphs and Transformers","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2407.19775","title":"Model Agnostic Hybrid Sharding For Heterogeneous Distributed Inference","created":"2024-07-29","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":"2601.20116","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":"2412.08911","title":"Goal-Conditioned Supervised Learning for Multi-Objective Recommendation","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2510.03051","title":"ZeroShotOpt: Towards Zero-Shot Pretrained Models for Efficient Black-Box Optimization","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2508.16420","title":"Hybrid Sequence Modeling and Reinforced Verification for Controllable Target-Conditioned Decision Making","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2602.08584","title":"Conditional Sequence Modeling for Safe Reinforcement Learning","created":"2026-02-09","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}],"next_cursor":null}