{"total":107,"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":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190,"area":null},{"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":"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":"2104.05859","title":"Rapid Exploration for Open-World Navigation with Latent Goal Models","created":"2021-04-12","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":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91,"area":"diffusion"},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89,"area":null},{"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":"2210.08323","title":"A Policy-Guided Imitation Approach for Offline Reinforcement Learning","created":"2022-10-15","cited_by_count":59,"area":"offlinerl"},{"id":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59,"area":null},{"id":"2301.13616","title":"Anti-Exploration by Random Network Distillation","created":"2023-01-31","cited_by_count":50,"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":"2305.02968","title":"Masked Trajectory Models for Prediction, Representation, and Control","created":"2023-05-04","cited_by_count":42,"area":"offlinerl"},{"id":"2310.08235","title":"GROOT: Learning to Follow Instructions by Watching Gameplay Videos","created":"2023-10-12","cited_by_count":42,"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":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2310.20141","title":"Contrastive Difference Predictive Coding","created":"2023-10-31","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":"2412.03782","title":"The broader spectrum of in-context learning","created":"2024-12-05","cited_by_count":35,"area":null},{"id":"2305.16554","title":"Emergent Agentic Transformer from Chain of Hindsight Experience","created":"2023-05-26","cited_by_count":33,"area":"agents"},{"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":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28,"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":"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":"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":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2405.08740","title":"Reinformer: Max-Return Sequence Modeling for Offline RL","created":"2024-05-14","cited_by_count":25,"area":"offlinerl"},{"id":"2206.03378","title":"Imitating Past Successes can be Very Suboptimal","created":"2022-06-07","cited_by_count":23,"area":"offlinerl"},{"id":"2306.03346","title":"Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data","created":"2023-06-06","cited_by_count":23,"area":null},{"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":"2305.16183","title":"Passive learning of active causal strategies in agents and language models","created":"2023-05-25","cited_by_count":21,"area":"agents"},{"id":"2311.02013","title":"SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learning","created":"2023-11-03","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":"2211.15457","title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning","created":"2022-11-28","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":"2304.13774","title":"Distance Weighted Supervised Learning for Offline Interaction Data","created":"2023-04-26","cited_by_count":18,"area":"offlinerl"},{"id":"2305.06289","title":"Learning Video-Conditioned Policies for Unseen Manipulation Tasks","created":"2023-05-10","cited_by_count":16,"area":null},{"id":"2109.02102","title":"Teaching Autoregressive Language Models Complex Tasks By Demonstration","created":"2021-09-05","cited_by_count":15,"area":null},{"id":"2203.13573","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","created":"2022-03-25","cited_by_count":14,"area":null},{"id":"2406.15149","title":"Gaussian Splatting to Real World Flight Navigation Transfer with Liquid Networks","created":"2024-06-21","cited_by_count":14,"area":null},{"id":"2306.14534","title":"CEIL: Generalized Contextual Imitation Learning","created":"2023-06-26","cited_by_count":13,"area":"offlinerl"},{"id":"2306.16803","title":"Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis","created":"2023-06-29","cited_by_count":13,"area":null},{"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":"2205.06595","title":"Upside-Down Reinforcement Learning Can Diverge in Stochastic Environments With Episodic Resets","created":"2022-05-13","cited_by_count":10,"area":null},{"id":"2402.05290","title":"Do Transformer World Models Give Better Policy Gradients?","created":"2024-02-07","cited_by_count":10,"area":"wm"},{"id":"2106.05526","title":"Simplifying Deep Reinforcement Learning via Self-Supervision","created":"2021-06-10","cited_by_count":9,"area":null},{"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":"2207.01570","title":"Goal-Conditioned Generators of Deep Policies","created":"2022-07-04","cited_by_count":9,"area":null},{"id":"2308.03526","title":"AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning","created":"2023-08-07","cited_by_count":9,"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":"2307.10867","title":"FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback","created":"2023-07-20","cited_by_count":7,"area":"alignment"},{"id":"2208.07587","title":"Making Reinforcement Learning Work on Swimmer","created":"2022-08-16","cited_by_count":6,"area":null},{"id":"2210.05158","title":"Reliable Conditioning of Behavioral Cloning for Offline Reinforcement Learning","created":"2022-10-11","cited_by_count":6,"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":"2410.03408","title":"Predictive Coding for Decision Transformer","created":"2024-10-04","cited_by_count":6,"area":"offlinerl"},{"id":"2411.13420","title":"Heuristically Adaptive Diffusion-Model Evolutionary Strategy","created":"2024-11-20","cited_by_count":6,"area":"diffusion"},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2507.09041","title":"Behavioral Exploration: Learning to Explore via In-Context Adaptation","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2601.18175","title":"Success Conditioning as Policy Improvement: The Optimization Problem Solved by Imitating Success","created":"2026-01-26","cited_by_count":4,"area":null},{"id":"2103.02225","title":"Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction","created":"2021-03-03","cited_by_count":3,"area":null},{"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":"2402.03923","title":"Return-Aligned Decision Transformer","created":"2024-02-06","cited_by_count":3,"area":"offlinerl"},{"id":"2508.00152","title":"GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration","created":"2025-07-31","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":"2310.03915","title":"Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control","created":"2023-10-05","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":"2505.21852","title":"A Provable Approach for End-to-End Safe Reinforcement Learning","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2512.21527","title":"Generative Actor Critic","created":"2025-12-25","cited_by_count":2,"area":"deeprl"},{"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":"2306.08810","title":"Deep Generative Models for Decision-Making and Control","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2308.16379","title":"Multi-Objective Decision Transformers for Offline Reinforcement Learning","created":"2023-08-31","cited_by_count":1,"area":"offlinerl"},{"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":"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":"2412.11410","title":"MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning","created":"2024-12-16","cited_by_count":1,"area":"offlinerl"},{"id":"2502.09854","title":"Scaling Multimodal Search and Recommendation with Small Language Models via Upside-Down Reinforcement Learning","created":"2025-02-14","cited_by_count":1,"area":null},{"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":"2509.25727","title":"Boundary-to-Region Supervision for Offline Safe Reinforcement Learning","created":"2025-09-30","cited_by_count":1,"area":"offlinerl"},{"id":"2510.25897","title":"MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency","created":"2025-10-29","cited_by_count":1,"area":"alignment"},{"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":"2308.14897","title":"Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning","created":"2023-08-28","cited_by_count":0,"area":"offlinerl"},{"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":"2406.13376","title":"Efficient Offline Reinforcement Learning: First Imitate, then Improve","created":"2024-06-19","cited_by_count":0,"area":"offlinerl"}],"next_cursor":"100"}