{"total":103,"rows":[{"id":"2511.14759","title":"$\\pi^{*}_{0.6}$: a VLA That Learns From Experience","created":"2025-11-18","cited_by_count":303,"area":"vla"},{"id":"2309.10150","title":"Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions","created":"2023-09-18","cited_by_count":131,"area":"offlinerl"},{"id":"2412.06685","title":"Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone","created":"2024-12-09","cited_by_count":79,"area":"offlinerl"},{"id":"2307.02484","title":"Elastic Decision Transformer","created":"2023-07-05","cited_by_count":67,"area":null},{"id":"2505.23458","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","created":"2025-05-29","cited_by_count":58,"area":"offlinerl"},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2505.07395","title":"ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning","created":"2025-05-12","cited_by_count":47,"area":"vla"},{"id":"2503.05153","title":"Generative Trajectory Stitching through Diffusion Composition","created":"2025-03-07","cited_by_count":41,"area":"diffusion"},{"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":"2402.03570","title":"Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning","created":"2024-02-05","cited_by_count":31,"area":"wm"},{"id":"2312.12275","title":"Emergence of In-Context Reinforcement Learning from Noise Distillation","created":"2023-12-19","cited_by_count":27,"area":null},{"id":"2401.11237","title":"Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View","created":"2024-01-20","cited_by_count":27,"area":"deeprl"},{"id":"2312.13716","title":"Critic-Guided Decision Transformer for Offline Reinforcement Learning","created":"2023-12-21","cited_by_count":26,"area":"offlinerl"},{"id":"2309.05915","title":"ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning","created":"2023-09-12","cited_by_count":25,"area":"offlinerl"},{"id":"2405.08740","title":"Reinformer: Max-Return Sequence Modeling for Offline RL","created":"2024-05-14","cited_by_count":25,"area":"offlinerl"},{"id":"2310.12955","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","created":"2023-10-19","cited_by_count":24,"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":"2306.14069","title":"Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets","created":"2023-06-24","cited_by_count":22,"area":"offlinerl"},{"id":"2509.06863","title":"floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL","created":"2025-09-08","cited_by_count":22,"area":"diffusion"},{"id":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2303.03747","title":"Graph Decision Transformer","created":"2023-03-07","cited_by_count":20,"area":"offlinerl"},{"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":"2410.09536","title":"TOP-ERL: Transformer-based Off-Policy Episodic Reinforcement Learning","created":"2024-10-12","cited_by_count":19,"area":"deeprl"},{"id":"2306.09459","title":"Recurrent Action Transformer with Memory","created":"2023-06-15","cited_by_count":17,"area":"offlinerl"},{"id":"2406.05427","title":"Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL","created":"2024-06-08","cited_by_count":15,"area":"ssm"},{"id":"2311.00267","title":"Rethinking Decision Transformer via Hierarchical Reinforcement Learning","created":"2023-11-01","cited_by_count":14,"area":"offlinerl"},{"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":"2405.18080","title":"HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning","created":"2024-05-28","cited_by_count":14,"area":"offlinerl"},{"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":"2506.10137","title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","created":"2025-06-11","cited_by_count":12,"area":"offlinerl"},{"id":"2403.07262","title":"A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective","created":"2024-03-12","cited_by_count":11,"area":"offlinerl"},{"id":"2402.17217","title":"Temporal Logic Specification-Conditioned Decision Transformer for Offline Safe Reinforcement Learning","created":"2024-02-27","cited_by_count":10,"area":"offlinerl"},{"id":"2502.17666","title":"Yes, Q-learning Helps Offline In-Context RL","created":"2025-02-24","cited_by_count":10,"area":"offlinerl"},{"id":"2405.17358","title":"Rethinking Transformers in Solving POMDPs","created":"2024-05-27","cited_by_count":9,"area":"deeprl"},{"id":"2410.24108","title":"Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers","created":"2024-10-31","cited_by_count":8,"area":"offlinerl"},{"id":"2402.02017","title":"Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning","created":"2024-02-03","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":"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":"2307.10936","title":"PASTA: Pretrained Action-State Transformer Agents","created":"2023-07-20","cited_by_count":6,"area":"agents"},{"id":"2406.06793","title":"PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer","created":"2024-06-10","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":"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":"2602.18015","title":"Flow Actor-Critic for Offline Reinforcement Learning","created":"2026-02-20","cited_by_count":6,"area":"offlinerl"},{"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":"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":"2506.01299","title":"Scalable In-Context Q-Learning","created":"2025-06-02","cited_by_count":5,"area":"wm"},{"id":"2403.18539","title":"Safe and Robust Reinforcement Learning: Principles and Practice","created":"2024-03-27","cited_by_count":4,"area":"deeprl"},{"id":"2405.18757","title":"Multi-objective Cross-task Learning via Goal-conditioned GPT-based Decision Transformers for Surgical Robot Task Automation","created":"2024-05-29","cited_by_count":4,"area":"offlinerl"},{"id":"2407.18414","title":"Adversarially Robust Decision Transformer","created":"2024-07-25","cited_by_count":4,"area":"offlinerl"},{"id":"2409.08062","title":"Q-value Regularized Decision ConvFormer for Offline Reinforcement Learning","created":"2024-09-12","cited_by_count":4,"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":"2402.03923","title":"Return-Aligned Decision Transformer","created":"2024-02-06","cited_by_count":3,"area":"offlinerl"},{"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":"2603.11099","title":"Graph Tokenization for Bridging Graphs and Transformers","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2311.00094","title":"A Tractable Inference Perspective of Offline RL","created":"2023-10-31","cited_by_count":2,"area":"offlinerl"},{"id":"2407.19775","title":"Model Agnostic Hybrid Sharding For Heterogeneous Distributed Inference","created":"2024-07-29","cited_by_count":2,"area":null},{"id":"2411.07760","title":"Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning","created":"2024-11-12","cited_by_count":2,"area":"offlinerl"},{"id":"2411.11327","title":"Enhancing Decision Transformer with Diffusion-Based Trajectory Branch Generation","created":"2024-11-18","cited_by_count":2,"area":"diffusion"},{"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":"2507.10174","title":"Should We Ever Prefer Decision Transformer for Offline Reinforcement Learning?","created":"2025-07-14","cited_by_count":2,"area":"offlinerl"},{"id":"2512.21527","title":"Generative Actor Critic","created":"2025-12-25","cited_by_count":2,"area":"deeprl"},{"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":"2402.12845","title":"MORE-3S:Multimodal-based Offline Reinforcement Learning with Shared Semantic Spaces","created":"2024-02-20","cited_by_count":1,"area":"offlinerl"},{"id":"2405.14374","title":"State-Constrained Offline Reinforcement Learning","created":"2024-05-23","cited_by_count":1,"area":"offlinerl"},{"id":"2411.11364","title":"Continual Task Learning through Adaptive Policy Self-Composition","created":"2024-11-18","cited_by_count":1,"area":"offlinerl"},{"id":"2412.08911","title":"Goal-Conditioned Supervised Learning for Multi-Objective Recommendation","created":"2024-12-12","cited_by_count":1,"area":null},{"id":"2501.06718","title":"DRDT3: Diffusion-Refined Decision Test-Time Training Model","created":"2025-01-12","cited_by_count":1,"area":"diffusion"},{"id":"2505.09114","title":"Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer","created":"2025-05-14","cited_by_count":1,"area":"offlinerl"},{"id":"2506.08463","title":"How to Provably Improve Return Conditioned Supervised Learning?","created":"2025-06-10","cited_by_count":1,"area":"offlinerl"},{"id":"2509.25966","title":"MUVLA: Learning to Explore Object Navigation via Map Understanding","created":"2025-09-30","cited_by_count":1,"area":"vla"},{"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":"2601.00167","title":"Online Finetuning Decision Transformers with Pure RL Gradients","created":"2026-01-01","cited_by_count":1,"area":"offlinerl"},{"id":"2601.15953","title":"Decoupling Return-to-Go for Efficient Decision Transformer","created":"2026-01-22","cited_by_count":1,"area":"offlinerl"},{"id":"2408.10517","title":"Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing","created":"2024-08-20","cited_by_count":0,"area":"ssm"},{"id":"2412.05675","title":"M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model","created":"2024-12-07","cited_by_count":0,"area":"offlinerl"},{"id":"2502.06491","title":"Model-Based Offline Reinforcement Learning with Reliability-Guaranteed Sequence Modeling","created":"2025-02-10","cited_by_count":0,"area":"offlinerl"},{"id":"2502.10473","title":"Diverse Transformer Decoding for Offline Reinforcement Learning Using Financial Algorithmic Approaches","created":"2025-02-13","cited_by_count":0,"area":"offlinerl"},{"id":"2503.02311","title":"Target Return Optimizer for Multi-Game Decision Transformer","created":"2025-03-04","cited_by_count":0,"area":"offlinerl"},{"id":"2505.20350","title":"Decision Flow Policy Optimization","created":"2025-05-26","cited_by_count":0,"area":"offlinerl"},{"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":"2509.26137","title":"Accelerating Transformers in Online RL","created":"2025-09-30","cited_by_count":0,"area":"deeprl"},{"id":"2510.05285","title":"Adjusting the Output of Decision Transformer with Action Gradient","created":"2025-10-06","cited_by_count":0,"area":"offlinerl"},{"id":"2512.14726","title":"Quantum Decision Transformers (QDT): Synergistic Entanglement and Interference for Offline Reinforcement Learning","created":"2025-12-09","cited_by_count":0,"area":"offlinerl"},{"id":"2602.05323","title":"GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RL","created":"2026-02-05","cited_by_count":0,"area":"offlinerl"},{"id":"2602.08584","title":"Conditional Sequence Modeling for Safe Reinforcement Learning","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.09207","title":"CausalGDP: Causality-Guided Diffusion Policies for Reinforcement Learning","created":"2026-02-09","cited_by_count":0,"area":"diffusion"},{"id":"2602.19582","title":"Advantage-based Temporal Attack in Reinforcement Learning","created":"2026-02-23","cited_by_count":0,"area":"deeprl"},{"id":"2602.19805","title":"Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing","created":"2026-02-23","cited_by_count":0,"area":"ssm"},{"id":"2603.03932","title":"Selecting Offline Reinforcement Learning Algorithms for Stochastic Network Control","created":"2026-03-04","cited_by_count":0,"area":"offlinerl"},{"id":"2605.06104","title":"Beyond Autoregressive RTG: Conditioning via Injection Outside Sequential Modeling in Decision Transformer","created":"2026-05-07","cited_by_count":0,"area":"offlinerl"},{"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":"2606.05208","title":"Transformer-Enhanced Reinforcement Learning: Fundamentals and Applications in Communication Networks","created":"2026-05-26","cited_by_count":0,"area":"deeprl"},{"id":"2606.08312","title":"Neuro-Symbolic Injection of LTLf Constraints in Autoregressive Reinforcement Learning Policies","created":"2026-06-06","cited_by_count":0,"area":"offlinerl"},{"id":"2608.02332","title":"Diffusion Policy with Behavioral Advantage Correction for Offline Reinforcement Learning","created":"2026-08-03","cited_by_count":0,"area":"diffusion"},{"id":"2608.23204","title":"Guided Riemannian Optimization (GuRO): Bridging Model Predictive Control and Decision Transformers","created":"2026-08-24","cited_by_count":0,"area":"offlinerl"},{"id":"2609.03667","title":"Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement Learning","created":"2026-09-03","cited_by_count":0,"area":"offlinerl"}],"next_cursor":"100"}