{"total":196,"rows":[{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808,"area":"agents"},{"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":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478,"area":"wm"},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407,"area":null},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328,"area":"wm"},{"id":"2511.14759","title":"$\\pi^{*}_{0.6}$: a VLA That Learns From Experience","created":"2025-11-18","cited_by_count":303,"area":"vla"},{"id":"2205.13636","title":"Quark: Controllable Text Generation with Reinforced Unlearning","created":"2022-05-26","cited_by_count":237,"area":"safety"},{"id":"2303.05479","title":"Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning","created":"2023-03-09","cited_by_count":237,"area":"offlinerl"},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195,"area":null},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190,"area":null},{"id":"2207.04179","title":"Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling","created":"2022-07-09","cited_by_count":127,"area":null},{"id":"2204.02372","title":"Jump-Start Reinforcement Learning","created":"2022-04-05","cited_by_count":112,"area":null},{"id":"2305.13122","title":"Policy Representation via Diffusion Probability Model for Reinforcement Learning","created":"2023-05-22","cited_by_count":112,"area":"diffusion"},{"id":"2210.14222","title":"PlanT: Explainable Planning Transformers via Object-Level Representations","created":"2022-10-25","cited_by_count":105,"area":null},{"id":"2407.16677","title":"From Imitation to Refinement -- Residual RL for Precise Assembly","created":"2024-07-23","cited_by_count":90,"area":null},{"id":"2310.17722","title":"Large Language Models as Generalizable Policies for Embodied Tasks","created":"2023-10-26","cited_by_count":86,"area":null},{"id":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81,"area":null},{"id":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77,"area":null},{"id":"2306.07180","title":"Diffusion Models for Black-Box Optimization","created":"2023-06-12","cited_by_count":76,"area":"diffusion"},{"id":"2302.07351","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning","created":"2023-02-14","cited_by_count":69,"area":"offlinerl"},{"id":"2307.02484","title":"Elastic Decision Transformer","created":"2023-07-05","cited_by_count":67,"area":null},{"id":"2307.03864","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","created":"2023-07-07","cited_by_count":63,"area":null},{"id":"2302.05206","title":"The Wisdom of Hindsight Makes Language Models Better Instruction Followers","created":"2023-02-10","cited_by_count":62,"area":"alignment"},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"2406.20083","title":"PoliFormer: Scaling On-Policy RL with Transformers Results in Masterful Navigators","created":"2024-06-28","cited_by_count":58,"area":"deeprl"},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2406.20095","title":"LLaRA: Supercharging Robot Learning Data for Vision-Language Policy","created":"2024-06-28","cited_by_count":52,"area":"mllm"},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"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":"2211.12740","title":"Masked Autoencoding for Scalable and Generalizable Decision Making","created":"2022-11-23","cited_by_count":45,"area":"offlinerl"},{"id":"2301.09816","title":"SMART: Self-supervised Multi-task pretrAining with contRol Transformers","created":"2023-01-24","cited_by_count":44,"area":null},{"id":"2306.14744","title":"ChiPFormer: Transferable Chip Placement via Offline Decision Transformer","created":"2023-06-26","cited_by_count":42,"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":"2307.01849","title":"Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning","created":"2023-07-04","cited_by_count":40,"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":"2307.16118","title":"MTD-GPT: A Multi-Task Decision-Making GPT Model for Autonomous Driving at Unsignalized Intersections","created":"2023-07-30","cited_by_count":38,"area":"driving"},{"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":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2305.00567","title":"Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL","created":"2023-04-30","cited_by_count":36,"area":null},{"id":"2304.08487","title":"Hyper-Decision Transformer for Efficient Online Policy Adaptation","created":"2023-04-17","cited_by_count":33,"area":"offlinerl"},{"id":"2408.06316","title":"Body Transformer: Leveraging Robot Embodiment for Policy Learning","created":"2024-08-12","cited_by_count":32,"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":"2205.10816","title":"Chain of Thought Imitation with Procedure Cloning","created":"2022-05-22","cited_by_count":30,"area":"lr"},{"id":"2206.07922","title":"Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications","created":"2022-06-16","cited_by_count":30,"area":null},{"id":"2211.08714","title":"Reward Gaming in Conditional Text Generation","created":"2022-11-16","cited_by_count":30,"area":null},{"id":"2305.15669","title":"PROTO: Iterative Policy Regularized Offline-to-Online Reinforcement Learning","created":"2023-05-25","cited_by_count":29,"area":"offlinerl"},{"id":"2410.05362","title":"LLMs Are In-Context Bandit Reinforcement Learners","created":"2024-10-07","cited_by_count":29,"area":null},{"id":"2210.06518","title":"Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories","created":"2022-10-12","cited_by_count":28,"area":"offlinerl"},{"id":"2306.14884","title":"Learning to Modulate pre-trained Models in RL","created":"2023-06-26","cited_by_count":28,"area":null},{"id":"2405.18418","title":"Hierarchical World Models as Visual Whole-Body Humanoid Controllers","created":"2024-05-28","cited_by_count":27,"area":"wm"},{"id":"2303.17396","title":"Finetuning from Offline Reinforcement Learning: Challenges, Trade-offs and Practical Solutions","created":"2023-03-30","cited_by_count":26,"area":"offlinerl"},{"id":"2305.16683","title":"Future-conditioned Unsupervised Pretraining for Decision Transformer","created":"2023-05-26","cited_by_count":26,"area":"offlinerl"},{"id":"2306.05167","title":"Decision S4: Efficient Sequence-Based RL via State Spaces Layers","created":"2023-06-08","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":"2311.03351","title":"Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization","created":"2023-11-06","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":"2504.14587","title":"Generative Auto-Bidding with Value-Guided Explorations","created":"2025-04-20","cited_by_count":23,"area":null},{"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":"2309.15178","title":"Zero-Shot Reinforcement Learning from Low Quality Data","created":"2023-09-26","cited_by_count":21,"area":null},{"id":"2402.09844","title":"Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent","created":"2024-02-15","cited_by_count":21,"area":null},{"id":"2411.02064","title":"Amortized Bayesian Experimental Design for Decision-Making","created":"2024-11-04","cited_by_count":21,"area":null},{"id":"2303.03747","title":"Graph Decision Transformer","created":"2023-03-07","cited_by_count":20,"area":"offlinerl"},{"id":"2307.10710","title":"Reparameterized Policy Learning for Multimodal Trajectory Optimization","created":"2023-07-20","cited_by_count":20,"area":null},{"id":"2312.06937","title":"Can a Transformer Represent a Kalman Filter?","created":"2023-12-12","cited_by_count":20,"area":null},{"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":"2306.13945","title":"Large Sequence Models for Sequential Decision-Making: A Survey","created":"2023-06-24","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":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2307.07909","title":"Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training","created":"2023-07-16","cited_by_count":18,"area":null},{"id":"2306.09459","title":"Recurrent Action Transformer with Memory","created":"2023-06-15","cited_by_count":17,"area":"offlinerl"},{"id":"2209.10447","title":"Hierarchical Decision Transformer","created":"2022-09-21","cited_by_count":16,"area":"offlinerl"},{"id":"2301.12203","title":"SaFormer: A Conditional Sequence Modeling Approach to Offline Safe Reinforcement Learning","created":"2023-01-28","cited_by_count":16,"area":"offlinerl"},{"id":"2308.09873","title":"Skill Transformer: A Monolithic Policy for Mobile Manipulation","created":"2023-08-19","cited_by_count":16,"area":null},{"id":"2403.06826","title":"In-context Exploration-Exploitation for Reinforcement Learning","created":"2024-03-11","cited_by_count":16,"area":"offlinerl"},{"id":"2406.12125","title":"Efficient Sequential Decision Making with Large Language Models","created":"2024-06-17","cited_by_count":16,"area":null},{"id":"2210.10763","title":"On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning","created":"2022-10-19","cited_by_count":15,"area":null},{"id":"2211.03074","title":"A Survey on Influence Maximization: From an ML-Based Combinatorial Optimization","created":"2022-11-06","cited_by_count":15,"area":null},{"id":"2211.14655","title":"How Crucial is Transformer in Decision Transformer?","created":"2022-11-26","cited_by_count":14,"area":"offlinerl"},{"id":"2306.12860","title":"Learning from Visual Observation via Offline Pretrained State-to-Go Transformer","created":"2023-06-22","cited_by_count":14,"area":null},{"id":"2405.20984","title":"Bayesian Design Principles for Offline-to-Online Reinforcement Learning","created":"2024-05-31","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":"2211.14296","title":"A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation","created":"2022-11-25","cited_by_count":13,"area":null},{"id":"2405.03379","title":"Reverse Forward Curriculum Learning for Extreme Sample and Demonstration Efficiency in Reinforcement Learning","created":"2024-05-06","cited_by_count":13,"area":"deeprl"},{"id":"2410.23450","title":"Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning","created":"2024-10-30","cited_by_count":13,"area":"offlinerl"},{"id":"2303.11191","title":"A Survey of Demonstration Learning","created":"2023-03-20","cited_by_count":12,"area":"offlinerl"},{"id":"2310.00311","title":"Efficient Planning with Latent Diffusion","created":"2023-09-30","cited_by_count":12,"area":"diffusion"},{"id":"2507.14057","title":"Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design","created":"2025-07-18","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":"2301.09544","title":"Learning to View: Decision Transformers for Active Object Detection","created":"2023-01-23","cited_by_count":11,"area":"offlinerl"},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"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":"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":"2405.17358","title":"Rethinking Transformers in Solving POMDPs","created":"2024-05-27","cited_by_count":9,"area":"deeprl"},{"id":"2412.18855","title":"Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL","created":"2024-12-25","cited_by_count":9,"area":"offlinerl"},{"id":"2303.16189","title":"Planning with Sequence Models through Iterative Energy Minimization","created":"2023-03-28","cited_by_count":8,"area":null},{"id":"2306.06253","title":"Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models","created":"2023-06-09","cited_by_count":8,"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"}],"next_cursor":"100"}