{"total":61,"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":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447,"area":null},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345,"area":"offlinerl"},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2103.03454","title":"Structured Scene Memory for Vision-Language Navigation","created":"2021-03-05","cited_by_count":95,"area":null},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90,"area":null},{"id":"1902.04257","title":"Deep Reinforcement Learning from Policy-Dependent Human Feedback","created":"2019-02-12","cited_by_count":56,"area":"alignment"},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2103.12944","title":"Scene-Intuitive Agent for Remote Embodied Visual Grounding","created":"2021-03-24","cited_by_count":49,"area":null},{"id":"2101.11071","title":"The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors","created":"2021-01-26","cited_by_count":41,"area":null},{"id":"2203.09773","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","created":"2022-03-18","cited_by_count":41,"area":null},{"id":"2502.10550","title":"Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning","created":"2025-02-14","cited_by_count":36,"area":"deeprl"},{"id":"2403.04317","title":"Online Adaptation of Language Models with a Memory of Amortized Contexts","created":"2024-03-07","cited_by_count":35,"area":null},{"id":"2310.08367","title":"MCU: An Evaluation Framework for Open-Ended Game Agents","created":"2023-10-12","cited_by_count":34,"area":null},{"id":"2505.15182","title":"ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection","created":"2025-05-21","cited_by_count":31,"area":"agents"},{"id":"2112.04907","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","created":"2021-12-07","cited_by_count":28,"area":"offlinerl"},{"id":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27,"area":null},{"id":"2206.05314","title":"Large-Scale Retrieval for Reinforcement Learning","created":"2022-06-10","cited_by_count":24,"area":"offlinerl"},{"id":"2205.14850","title":"Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning","created":"2022-05-30","cited_by_count":22,"area":"offlinerl"},{"id":"2203.14708","title":"Object Memory Transformer for Object Goal Navigation","created":"2022-03-24","cited_by_count":20,"area":null},{"id":"2101.00240","title":"A Survey on Deep Reinforcement Learning for Audio-Based Applications","created":"2021-01-01","cited_by_count":17,"area":null},{"id":"2107.06011","title":"Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation","created":"2021-07-13","cited_by_count":17,"area":null},{"id":"2112.09477","title":"Learning Reward Machines: A Study in Partially Observable Reinforcement Learning","created":"2021-12-17","cited_by_count":16,"area":null},{"id":"2202.03735","title":"Navigating to Objects in Unseen Environments by Distance Prediction","created":"2022-02-08","cited_by_count":16,"area":null},{"id":"2208.12345","title":"Light-weight probing of unsupervised representations for Reinforcement Learning","created":"2022-08-25","cited_by_count":15,"area":null},{"id":"2211.15612","title":"Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning","created":"2022-11-28","cited_by_count":12,"area":"offlinerl"},{"id":"2404.18243","title":"LEGENT: Open Platform for Embodied Agents","created":"2024-04-28","cited_by_count":12,"area":"wm"},{"id":"2103.11374","title":"MaAST: Map Attention with Semantic Transformersfor Efficient Visual Navigation","created":"2021-03-21","cited_by_count":11,"area":null},{"id":"2207.13649","title":"Explain My Surprise: Learning Efficient Long-Term Memory by Predicting Uncertain Outcomes","created":"2022-07-27","cited_by_count":11,"area":null},{"id":"2410.04659","title":"ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models","created":"2024-10-07","cited_by_count":11,"area":"mllm"},{"id":"1709.03969","title":"Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds","created":"2017-09-12","cited_by_count":8,"area":"alignment"},{"id":"2102.06042","title":"Modeling the Interaction between Agents in Cooperative Multi-Agent Reinforcement Learning","created":"2021-02-10","cited_by_count":7,"area":null},{"id":"2405.03064","title":"RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation","created":"2024-05-05","cited_by_count":7,"area":"deeprl"},{"id":"2110.09018","title":"Reinforcement Learning-Based Coverage Path Planning with Implicit Cellular Decomposition","created":"2021-10-18","cited_by_count":6,"area":null},{"id":"2211.13337","title":"Multi-Environment Pretraining Enables Transfer to Action Limited Datasets","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2409.16824","title":"Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observability","created":"2024-09-25","cited_by_count":5,"area":"deeprl"},{"id":"2412.06531","title":"Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation","created":"2024-12-09","cited_by_count":5,"area":"deeprl"},{"id":"2202.12174","title":"Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?","created":"2022-02-24","cited_by_count":4,"area":null},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2508.16821","title":"PuzzleJAX: A Benchmark for Reasoning and Learning","created":"2025-08-22","cited_by_count":4,"area":"lr"},{"id":"2110.07171","title":"SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation","created":"2021-10-14","cited_by_count":3,"area":null},{"id":"2110.11443","title":"Off-Dynamics Inverse Reinforcement Learning from Hetero-Domain","created":"2021-10-21","cited_by_count":3,"area":"offlinerl"},{"id":"2404.07209","title":"Deep Reinforcement Learning Based Toolpath Generation for Thermal Uniformity in Laser Powder Bed Fusion Process","created":"2024-02-17","cited_by_count":3,"area":null},{"id":"2106.03748","title":"Towards robust and domain agnostic reinforcement learning competitions","created":"2021-06-07","cited_by_count":2,"area":null},{"id":"2106.14117","title":"Graph Convolutional Memory using Topological Priors","created":"2021-06-27","cited_by_count":2,"area":null},{"id":"2202.01534","title":"Influence-Augmented Local Simulators: A Scalable Solution for Fast Deep RL in Large Networked Systems","created":"2022-02-03","cited_by_count":2,"area":null},{"id":"2504.12045","title":"pix2pockets: Shot Suggestions in 8-Ball Pool from a Single Image in the Wild","created":"2025-04-16","cited_by_count":2,"area":"deeprl"},{"id":"2106.10533","title":"Learning to Reach, Swim, Walk and Fly in One Trial: Data-Driven Control with Scarce Data and Side Information","created":"2021-06-19","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":"2401.08121","title":"CycLight: learning traffic signal cooperation with a cycle-level strategy","created":"2024-01-16","cited_by_count":1,"area":"deeprl"},{"id":"1909.03200","title":"Mature GAIL: Imitation Learning for Low-level and High-dimensional Input using Global Encoder and Cost Transformation","created":"2019-09-07","cited_by_count":0,"area":"offlinerl"},{"id":"2103.16732","title":"Simultaneous Navigation and Construction Benchmarking Environments","created":"2021-03-31","cited_by_count":0,"area":null},{"id":"2104.10845","title":"Optimize Neural Fictitious Self-Play in Regret Minimization Thinking","created":"2021-04-22","cited_by_count":0,"area":null},{"id":"2106.08849","title":"How memory architecture affects learning in a simple POMDP: the two-hypothesis testing problem","created":"2021-06-16","cited_by_count":0,"area":null},{"id":"2202.07275","title":"HiMA: A Fast and Scalable History-based Memory Access Engine for Differentiable Neural Computer","created":"2022-02-15","cited_by_count":0,"area":null},{"id":"2209.13489","title":"Reward Learning using Structural Motifs in Inverse Reinforcement Learning","created":"2022-09-25","cited_by_count":0,"area":"offlinerl"},{"id":"2210.03269","title":"Multi-agent Deep Covering Skill Discovery","created":"2022-10-07","cited_by_count":0,"area":null},{"id":"2210.15908","title":"Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport","created":"2022-10-28","cited_by_count":0,"area":null},{"id":"2302.06872","title":"Adaptive Value Decomposition with Greedy Marginal Contribution Computation for Cooperative Multi-Agent Reinforcement Learning","created":"2023-02-14","cited_by_count":0,"area":null},{"id":"2511.21356","title":"Hybrid-AIRL: Enhancing Inverse Reinforcement Learning with Supervised Expert Guidance","created":"2025-11-26","cited_by_count":0,"area":"offlinerl"},{"id":"2604.08756","title":"Artifacts as Memory Beyond the Agent Boundary","created":"2026-04-09","cited_by_count":0,"area":null}],"next_cursor":null}