{"total":102,"rows":[{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546,"area":"offlinerl"},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644,"area":"wm"},{"id":"2211.15657","title":"Is Conditional Generative Modeling all you need for Decision-Making?","created":"2022-11-28","cited_by_count":516,"area":"diffusion"},{"id":"2511.14759","title":"$\\pi^{*}_{0.6}$: a VLA That Learns From Experience","created":"2025-11-18","cited_by_count":303,"area":"vla"},{"id":"2302.08582","title":"Pretraining Language Models with Human Preferences","created":"2023-02-16","cited_by_count":247,"area":"alignment"},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2112.10751","title":"RvS: What is Essential for Offline RL via Supervised Learning?","created":"2021-12-20","cited_by_count":185,"area":"offlinerl"},{"id":"2402.10207","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment","created":"2024-02-15","cited_by_count":175,"area":"alignment"},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158,"area":null},{"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":"2304.01203","title":"Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning","created":"2023-04-03","cited_by_count":121,"area":null},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"id":"2209.03993","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","created":"2022-09-08","cited_by_count":103,"area":"offlinerl"},{"id":"2311.13443","title":"Guided Flows for Generative Modeling and Decision Making","created":"2023-11-22","cited_by_count":101,"area":"diffusion"},{"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":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77,"area":"offlinerl"},{"id":"2206.01079","title":"When does return-conditioned supervised learning work for offline reinforcement learning?","created":"2022-06-02","cited_by_count":76,"area":"offlinerl"},{"id":"2205.15967","title":"You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments","created":"2022-05-31","cited_by_count":63,"area":"offlinerl"},{"id":"2210.08323","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","created":"2022-10-15","cited_by_count":59,"area":"offlinerl"},{"id":"2505.23458","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","created":"2025-05-29","cited_by_count":58,"area":"offlinerl"},{"id":"2210.13435","title":"Dichotomy of Control: Separating What You Can Control from What You Cannot","created":"2022-10-24","cited_by_count":47,"area":"offlinerl"},{"id":"2310.09971","title":"AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents","created":"2023-10-15","cited_by_count":41,"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":"2305.16217","title":"Beyond Reward: Offline Preference-guided Policy Optimization","created":"2023-05-25","cited_by_count":35,"area":"alignment"},{"id":"2309.06599","title":"Reasoning with Latent Diffusion in Offline Reinforcement Learning","created":"2023-09-12","cited_by_count":33,"area":"diffusion"},{"id":"2405.17098","title":"Q-value Regularized Transformer for Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":29,"area":"offlinerl"},{"id":"2110.06206","title":"StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learning","created":"2021-10-12","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":"2403.19918","title":"CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning","created":"2024-03-29","cited_by_count":27,"area":"driving"},{"id":"2305.16683","title":"Future-conditioned Unsupervised Pretraining for Decision Transformer","created":"2023-05-26","cited_by_count":26,"area":"offlinerl"},{"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":"2312.13716","title":"Critic-Guided Decision Transformer for Offline Reinforcement Learning","created":"2023-12-21","cited_by_count":26,"area":"offlinerl"},{"id":"2504.16925","title":"Latent Diffusion Planning for Imitation Learning","created":"2025-04-23","cited_by_count":26,"area":"diffusion"},{"id":"2204.05036","title":"Pareto Conditioned Networks","created":"2022-04-11","cited_by_count":25,"area":null},{"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":"2602.12099","title":"GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning","created":"2026-02-12","cited_by_count":24,"area":"wm"},{"id":"2206.03378","title":"Imitating Past Successes can be Very Suboptimal","created":"2022-06-07","cited_by_count":23,"area":"offlinerl"},{"id":"2306.13085","title":"Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting","created":"2023-06-22","cited_by_count":22,"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":"2206.00695","title":"Know Your Boundaries: The Necessity of Explicit Behavioral Cloning in Offline RL","created":"2022-06-01","cited_by_count":21,"area":"offlinerl"},{"id":"2303.03747","title":"Graph Decision Transformer","created":"2023-03-07","cited_by_count":20,"area":"offlinerl"},{"id":"2305.14550","title":"When should we prefer Decision Transformers for Offline Reinforcement Learning?","created":"2023-05-23","cited_by_count":20,"area":"offlinerl"},{"id":"2310.03718","title":"Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning","created":"2023-10-05","cited_by_count":18,"area":null},{"id":"2503.03707","title":"Curating Demonstrations using Online Experience","created":"2025-03-05","cited_by_count":18,"area":null},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2305.06289","title":"Learning Video-Conditioned Policies for Unseen Manipulation Tasks","created":"2023-05-10","cited_by_count":16,"area":null},{"id":"2306.14534","title":"CEIL: Generalized Contextual Imitation Learning","created":"2023-06-26","cited_by_count":13,"area":"offlinerl"},{"id":"2309.01448","title":"Hundreds Guide Millions: Adaptive Offline Reinforcement Learning with Expert Guidance","created":"2023-09-04","cited_by_count":13,"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":"2602.09021","title":"$\\chi_{0}$: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies","created":"2026-02-09","cited_by_count":12,"area":null},{"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":"2202.11960","title":"All You Need Is Supervised Learning: From Imitation Learning to Meta-RL With Upside Down RL","created":"2022-02-24","cited_by_count":9,"area":"offlinerl"},{"id":"2210.05125","title":"Human-AI Coordination via Human-Regularized Search and Learning","created":"2022-10-11","cited_by_count":8,"area":"offlinerl"},{"id":"2306.14479","title":"Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization","created":"2023-06-26","cited_by_count":8,"area":"offlinerl"},{"id":"2211.06407","title":"Control Transformer: Robot Navigation in Unknown Environments through PRM-Guided Return-Conditioned Sequence Modeling","created":"2022-11-11","cited_by_count":6,"area":null},{"id":"2307.02752","title":"Offline Reinforcement Learning with Imbalanced Datasets","created":"2023-07-06","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":"2606.11087","title":"Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning","created":"2026-06-09","cited_by_count":6,"area":"offlinerl"},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2403.18454","title":"Scaling Vision-and-Language Navigation With Offline RL","created":"2024-03-27","cited_by_count":5,"area":"offlinerl"},{"id":"2407.16970","title":"Towards Aligning Language Models with Textual Feedback","created":"2024-07-24","cited_by_count":5,"area":"alignment"},{"id":"2507.09041","title":"Behavioral Exploration: Learning to Explore via In-Context Adaptation","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2110.14464","title":"Learning from demonstrations with SACR2: Soft Actor-Critic with Reward Relabeling","created":"2021-10-27","cited_by_count":4,"area":"offlinerl"},{"id":"2407.16807","title":"In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning","created":"2024-07-23","cited_by_count":4,"area":"deeprl"},{"id":"2407.18414","title":"Adversarially Robust Decision Transformer","created":"2024-07-25","cited_by_count":4,"area":"offlinerl"},{"id":"2411.18195","title":"Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance","created":"2024-11-27","cited_by_count":4,"area":"deeprl"},{"id":"2606.05414","title":"When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories","created":"2026-06-03","cited_by_count":4,"area":"agents"},{"id":"2202.12742","title":"Learning Relative Return Policies With Upside-Down Reinforcement Learning","created":"2022-02-23","cited_by_count":3,"area":null},{"id":"2210.12272","title":"Implicit Offline Reinforcement Learning via Supervised Learning","created":"2022-10-21","cited_by_count":3,"area":"offlinerl"},{"id":"2302.05507","title":"Language Decision Transformers with Exponential Tilt for Interactive Text Environments","created":"2023-02-10","cited_by_count":3,"area":"offlinerl"},{"id":"2408.15593","title":"Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning","created":"2024-08-28","cited_by_count":3,"area":"offlinerl"},{"id":"2602.11399","title":"Can We Really Learn One Representation to Optimize All Rewards?","created":"2026-02-11","cited_by_count":3,"area":"deeprl"},{"id":"2305.11340","title":"Bayesian Reparameterization of Reward-Conditioned Reinforcement Learning with Energy-based Models","created":"2023-05-18","cited_by_count":2,"area":null},{"id":"2311.00094","title":"A Tractable Inference Perspective of Offline RL","created":"2023-10-31","cited_by_count":2,"area":"offlinerl"},{"id":"2401.11630","title":"Solving Offline Reinforcement Learning with Decision Tree Regression","created":"2024-01-21","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":"2501.19128","title":"Shaping Sparse Rewards in Reinforcement Learning: A Semi-supervised Approach","created":"2025-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2505.21852","title":"A Provable Approach for End-to-End Safe Reinforcement Learning","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2201.03834","title":"STIR$^2$: Reward Relabelling for combined Reinforcement and Imitation Learning on sparse-reward tasks","created":"2022-01-11","cited_by_count":1,"area":"offlinerl"},{"id":"2303.08909","title":"Latent-Conditioned Policy Gradient for Multi-Objective Deep Reinforcement Learning","created":"2023-03-15","cited_by_count":1,"area":null},{"id":"2404.12150","title":"Aligning language models with human preferences","created":"2024-04-18","cited_by_count":1,"area":"alignment"},{"id":"2406.02013","title":"Mamba as Decision Maker: Exploring Multi-scale Sequence Modeling in Offline Reinforcement Learning","created":"2024-06-04","cited_by_count":1,"area":"ssm"},{"id":"2506.08463","title":"How to Provably Improve Return Conditioned Supervised Learning?","created":"2025-06-10","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":"2603.05066","title":"Reward-Conditioned Reinforcement Learning","created":"2026-03-05","cited_by_count":1,"area":"alignment"},{"id":"2606.24231","title":"FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.32027","title":"Freeform Preference Learning for Robotic Manipulation","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2609.21617","title":"CounterPlay: Counterfactual Post-Training for Self-Play Driving Policies","created":"2026-09-18","cited_by_count":1,"area":"driving"},{"id":"2307.12968","title":"A Connection between One-Step Regularization and Critic Regularization in Reinforcement Learning","created":"2023-07-24","cited_by_count":0,"area":"offlinerl"},{"id":"2309.16291","title":"Efficiency Separation between RL Methods: Model-Free, Model-Based and Goal-Conditioned","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2405.00410","title":"UCB-driven Utility Function Search for Multi-objective Reinforcement Learning","created":"2024-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2406.10795","title":"Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2412.11253","title":"Are Expressive Models Truly Necessary for Offline RL?","created":"2024-12-15","cited_by_count":0,"area":"offlinerl"},{"id":"2502.05672","title":"On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers","created":"2025-02-08","cited_by_count":0,"area":"offlinerl"},{"id":"2509.02458","title":"Generative Sequential Notification Optimization via Multi-Objective Decision Transformers","created":"2025-09-02","cited_by_count":0,"area":"offlinerl"},{"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":"2609.34467","title":"Alignment-Guided Flow Transformer for Efficient Vision-Language-Action Policy Learning","created":"2026-09-28","cited_by_count":0,"area":"vla"},{"id":"2609.34851","title":"Learning High-Risk High-Precision Motion Control","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2610.00729","title":"Reward as Observation: Learning Reward-Based Policies for Rapid Adaptation","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":"100"}