{"total":125,"rows":[{"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":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290,"area":null},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258,"area":null},{"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":"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":"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":"2212.07489","title":"SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":122,"area":null},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101,"area":null},{"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":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81,"area":null},{"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":"2312.01072","title":"A Survey of Temporal Credit Assignment in Deep Reinforcement Learning","created":"2023-12-02","cited_by_count":59,"area":null},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2504.11054","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","created":"2025-04-15","cited_by_count":56,"area":"deeprl"},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48,"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":"2301.10034","title":"Open-World Multi-Task Control Through Goal-Aware Representation Learning and Adaptive Horizon Prediction","created":"2023-01-21","cited_by_count":39,"area":null},{"id":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36,"area":null},{"id":"2206.10786","title":"Generative Pretraining for Black-Box Optimization","created":"2022-06-22","cited_by_count":36,"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":"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":"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":"2405.08740","title":"Reinformer: Max-Return Sequence Modeling for Offline RL","created":"2024-05-14","cited_by_count":25,"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":"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":"2410.07071","title":"Retrieval-Augmented Decision Transformer: External Memory for In-context RL","created":"2024-10-09","cited_by_count":21,"area":"rag"},{"id":"2504.07896","title":"Fast Adaptation with Behavioral Foundation Models","created":"2025-04-10","cited_by_count":21,"area":"deeprl"},{"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":"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":"2203.13573","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","created":"2022-03-25","cited_by_count":14,"area":null},{"id":"2211.14655","title":"How Crucial is Transformer in Decision Transformer?","created":"2022-11-26","cited_by_count":14,"area":"offlinerl"},{"id":"2410.22391","title":"A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks","created":"2024-10-29","cited_by_count":14,"area":"deeprl"},{"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":"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":"2310.00311","title":"Efficient Planning with Latent Diffusion","created":"2023-09-30","cited_by_count":12,"area":"diffusion"},{"id":"2506.10137","title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","created":"2025-06-11","cited_by_count":12,"area":"offlinerl"},{"id":"2507.07995","title":"Single-pass Adaptive Image Tokenization for Minimum Program Search","created":"2025-07-10","cited_by_count":12,"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":"2301.12876","title":"Guiding Online Reinforcement Learning with Action-Free Offline Pretraining","created":"2023-01-30","cited_by_count":11,"area":"offlinerl"},{"id":"2602.03025","title":"RC-GRPO: Reward-Conditioned Group Relative Policy Optimization for Multi-Turn Tool Calling Agents","created":"2026-02-03","cited_by_count":11,"area":"lr"},{"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":"2303.03391","title":"Decision Transformer under Random Frame Dropping","created":"2023-03-03","cited_by_count":10,"area":"offlinerl"},{"id":"2402.05290","title":"Do Transformer World Models Give Better Policy Gradients?","created":"2024-02-07","cited_by_count":10,"area":"wm"},{"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":"2501.19400","title":"Vintix: Action Model via In-Context Reinforcement Learning","created":"2025-01-31","cited_by_count":10,"area":"deeprl"},{"id":"2505.21974","title":"BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RL","created":"2025-05-28","cited_by_count":10,"area":null},{"id":"2101.04750","title":"Linear Representation Meta-Reinforcement Learning for Instant Adaptation","created":"2021-01-12","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":"2204.05027","title":"Exploring the Pareto front of multi-objective COVID-19 mitigation policies using reinforcement learning","created":"2022-04-11","cited_by_count":9,"area":null},{"id":"2207.01570","title":"Goal-Conditioned Generators of Deep Policies","created":"2022-07-04","cited_by_count":9,"area":null},{"id":"2412.10410","title":"GROOT-2: Weakly Supervised Multi-Modal Instruction Following Agents","created":"2024-12-07","cited_by_count":9,"area":null},{"id":"2306.07541","title":"A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning","created":"2023-06-13","cited_by_count":8,"area":"offlinerl"},{"id":"2108.02096","title":"Policy Gradients Incorporating the Future","created":"2021-08-04","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":"2411.13420","title":"Heuristically Adaptive Diffusion-Model Evolutionary Strategy","created":"2024-11-20","cited_by_count":6,"area":"diffusion"},{"id":"2506.15446","title":"Zero-Shot Reinforcement Learning Under Partial Observability","created":"2025-06-18","cited_by_count":6,"area":"deeprl"},{"id":"2510.06288","title":"BuilderBench: The Building Blocks of Intelligent Agents","created":"2025-10-07","cited_by_count":6,"area":"agents"},{"id":"2303.07519","title":"Architext: Language-Driven Generative Architecture Design","created":"2023-03-13","cited_by_count":5,"area":null},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"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":"2407.18414","title":"Adversarially Robust Decision Transformer","created":"2024-07-25","cited_by_count":4,"area":"offlinerl"},{"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":"2202.12742","title":"Learning Relative Return Policies With Upside-Down Reinforcement Learning","created":"2022-02-23","cited_by_count":3,"area":null},{"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":"2402.03923","title":"Return-Aligned Decision Transformer","created":"2024-02-06","cited_by_count":3,"area":"offlinerl"},{"id":"2402.17501","title":"Intensive Care as One Big Sequence Modeling Problem","created":"2024-02-27","cited_by_count":3,"area":null},{"id":"2404.07351","title":"A Transformer-Based Model for the Prediction of Human Gaze Behavior on Videos","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2508.00152","title":"GeoExplorer: Active Geo-localization with Curiosity-Driven Exploration","created":"2025-07-31","cited_by_count":3,"area":"deeprl"},{"id":"2510.09596","title":"BaNEL: Exploration Posteriors for Generative Modeling Using Only Negative Rewards","created":"2025-10-10","cited_by_count":3,"area":null},{"id":"2603.13733","title":"Implicit Maximum Likelihood Estimation for Real-time Generative Model Predictive Control","created":"2026-03-14","cited_by_count":3,"area":null},{"id":"2109.15050","title":"An Offline Deep Reinforcement Learning for Maintenance Decision-Making","created":"2021-09-28","cited_by_count":2,"area":"offlinerl"},{"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":"2407.19380","title":"Empowering Clinicians with Medical Decision Transformers: A Framework for Sepsis Treatment","created":"2024-07-28","cited_by_count":2,"area":null},{"id":"2505.21852","title":"A Provable Approach for End-to-End Safe Reinforcement Learning","created":"2025-05-28","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}