{"total":90,"rows":[{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872,"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":"2305.17144","title":"Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory","created":"2023-05-25","cited_by_count":289,"area":"agents"},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116,"area":null},{"id":"2206.04114","title":"Deep Hierarchical Planning from Pixels","created":"2022-06-08","cited_by_count":101,"area":"wm"},{"id":"2305.02195","title":"CALM: Conditional Adversarial Latent Models for Directable Virtual Characters","created":"2023-05-02","cited_by_count":94,"area":null},{"id":"2105.13231","title":"AndroidEnv: A Reinforcement Learning Platform for Android","created":"2021-05-27","cited_by_count":90,"area":null},{"id":"2404.10179","title":"Scaling Instructable Agents Across Many Simulated Worlds","created":"2024-03-13","cited_by_count":71,"area":null},{"id":"2311.02058","title":"LOTUS: Continual Imitation Learning for Robot Manipulation Through Unsupervised Skill Discovery","created":"2023-11-03","cited_by_count":67,"area":"offlinerl"},{"id":"2310.03720","title":"SteP: Stacked LLM Policies for Web Actions","created":"2023-10-05","cited_by_count":66,"area":null},{"id":"2312.09238","title":"Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft","created":"2023-12-14","cited_by_count":61,"area":null},{"id":"2109.06668","title":"Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain","created":"2021-09-14","cited_by_count":58,"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":"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":"2111.13394","title":"Non-IID data and Continual Learning processes in Federated Learning: A long road ahead","created":"2021-11-26","cited_by_count":36,"area":null},{"id":"2303.16563","title":"Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks","created":"2023-03-29","cited_by_count":36,"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":"2112.04907","title":"JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learning","created":"2021-12-07","cited_by_count":28,"area":"offlinerl"},{"id":"2202.06626","title":"MuZero with Self-competition for Rate Control in VP9 Video Compression","created":"2022-02-14","cited_by_count":28,"area":null},{"id":"2211.10445","title":"Building a Subspace of Policies for Scalable Continual Learning","created":"2022-11-18","cited_by_count":28,"area":null},{"id":"2102.06741","title":"Discovery of Options via Meta-Learned Subgoals","created":"2021-02-12","cited_by_count":27,"area":null},{"id":"2207.07730","title":"How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition","created":"2022-07-15","cited_by_count":27,"area":null},{"id":"2111.03189","title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","created":"2021-11-04","cited_by_count":26,"area":null},{"id":"2407.15325","title":"Odyssey: Empowering Minecraft Agents with Open-World Skills","created":"2024-07-22","cited_by_count":26,"area":"agents"},{"id":"2210.06964","title":"Causality-driven Hierarchical Structure Discovery for Reinforcement Learning","created":"2022-10-13","cited_by_count":24,"area":null},{"id":"2208.08731","title":"Intelligent problem-solving as integrated hierarchical reinforcement learning","created":"2022-08-18","cited_by_count":21,"area":null},{"id":"2204.06127","title":"Reinforcement learning on graphs: A survey","created":"2022-04-13","cited_by_count":20,"area":null},{"id":"2211.07819","title":"General Intelligence Requires Rethinking Exploration","created":"2022-11-15","cited_by_count":20,"area":null},{"id":"2103.07607","title":"Solving Compositional Reinforcement Learning Problems via Task Reduction","created":"2021-03-13","cited_by_count":19,"area":null},{"id":"2506.21872","title":"A Survey of Continual Reinforcement Learning","created":"2025-06-27","cited_by_count":18,"area":"deeprl"},{"id":"2106.00133","title":"AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning","created":"2021-05-31","cited_by_count":17,"area":null},{"id":"2307.06870","title":"Embodied Lifelong Learning for Task and Motion Planning","created":"2023-07-13","cited_by_count":17,"area":null},{"id":"2112.04467","title":"CoMPS: Continual Meta Policy Search","created":"2021-12-08","cited_by_count":15,"area":null},{"id":"2303.10571","title":"Reinforcement Learning Friendly Vision-Language Model for Minecraft","created":"2023-03-19","cited_by_count":14,"area":"mllm"},{"id":"2010.03133","title":"Provable Hierarchical Imitation Learning via EM","created":"2020-10-07","cited_by_count":10,"area":"offlinerl"},{"id":"2103.04067","title":"Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning","created":"2021-03-06","cited_by_count":9,"area":null},{"id":"2102.11137","title":"Program Synthesis Guided Reinforcement Learning for Partially Observed Environments","created":"2021-02-22","cited_by_count":8,"area":null},{"id":"2303.04912","title":"Embodied Active Learning of Relational State Abstractions for Bilevel Planning","created":"2023-03-08","cited_by_count":8,"area":null},{"id":"2310.05167","title":"Hieros: Hierarchical Imagination on Structured State Space Sequence World Models","created":"2023-10-08","cited_by_count":8,"area":"wm"},{"id":"2301.00141","title":"Self-Activating Neural Ensembles for Continual Reinforcement Learning","created":"2022-12-31","cited_by_count":7,"area":null},{"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":"2307.07091","title":"Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning","created":"2023-07-13","cited_by_count":6,"area":"offlinerl"},{"id":"2309.17011","title":"Feature Interaction Aware Automated Data Representation Transformation","created":"2023-09-29","cited_by_count":6,"area":null},{"id":"2509.22442","title":"Learning to Ball: Composing Policies for Long-Horizon Basketball Moves","created":"2025-09-26","cited_by_count":6,"area":"deeprl"},{"id":"2109.14737","title":"Unlocking the potential of deep learning for marine ecology: overview, applications, and outlook","created":"2021-09-29","cited_by_count":5,"area":null},{"id":"2505.12278","title":"Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learning","created":"2025-05-18","cited_by_count":5,"area":"deeprl"},{"id":"2506.13253","title":"Distinct Computations Emerge From Compositional Curricula in In-Context Learning","created":"2025-06-16","cited_by_count":5,"area":null},{"id":"2507.14850","title":"Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems","created":"2025-07-20","cited_by_count":5,"area":null},{"id":"2106.01741","title":"Lifetime policy reuse and the importance of task capacity","created":"2021-06-03","cited_by_count":4,"area":null},{"id":"2205.05230","title":"Developing cooperative policies for multi-stage reinforcement learning tasks","created":"2022-05-11","cited_by_count":4,"area":null},{"id":"2107.05445","title":"Disentangling Transfer and Interference in Multi-Domain Learning","created":"2021-07-02","cited_by_count":3,"area":null},{"id":"2305.14177","title":"ChemGymRL: An Interactive Framework for Reinforcement Learning for Digital Chemistry","created":"2023-05-23","cited_by_count":3,"area":null},{"id":"2102.12205","title":"Enabling the Network to Surf the Internet","created":"2021-02-24","cited_by_count":2,"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":"2109.06580","title":"Continuous Homeostatic Reinforcement Learning for Self-Regulated Autonomous Agents","created":"2021-09-14","cited_by_count":2,"area":null},{"id":"2204.02390","title":"Learning Pneumatic Non-Prehensile Manipulation with a Mobile Blower","created":"2022-04-05","cited_by_count":2,"area":null},{"id":"2207.02295","title":"Implementing Reinforcement Learning Datacenter Congestion Control in NVIDIA NICs","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2209.08112","title":"Optimizing Industrial HVAC Systems with Hierarchical Reinforcement Learning","created":"2022-09-16","cited_by_count":2,"area":null},{"id":"2402.06501","title":"Scalable Interactive Machine Learning for Future Command and Control","created":"2024-02-09","cited_by_count":2,"area":null},{"id":"2406.09835","title":"I Know How: Combining Prior Policies to Solve New Tasks","created":"2024-06-14","cited_by_count":2,"area":"deeprl"},{"id":"2505.12508","title":"InnateCoder: Learning Programmatic Options with Foundation Models","created":"2025-05-18","cited_by_count":2,"area":"deeprl"},{"id":"2105.13806","title":"DRL: Deep Reinforcement Learning for Intelligent Robot Control -- Concept, Literature, and Future","created":"2021-04-20","cited_by_count":1,"area":null},{"id":"2105.14471","title":"Reducing the Deployment-Time Inference Control Costs of Deep Reinforcement Learning Agents via an Asymmetric Architecture","created":"2021-05-30","cited_by_count":1,"area":null},{"id":"2202.06987","title":"ASC me to Do Anything: Multi-task Training for Embodied AI","created":"2022-02-14","cited_by_count":1,"area":null},{"id":"2204.11370","title":"Deep Reinforcement Learning Using a Low-Dimensional Observation Filter for Visual Complex Video Game Playing","created":"2022-04-24","cited_by_count":1,"area":null},{"id":"2311.14270","title":"Efficient Open-world Reinforcement Learning via Knowledge Distillation and Autonomous Rule Discovery","created":"2023-11-24","cited_by_count":1,"area":"distill"},{"id":"2405.06535","title":"Controllable Image Generation with Composed Parallel Token Prediction","created":"2024-05-10","cited_by_count":1,"area":null},{"id":"2407.08250","title":"Gradient Boosting Reinforcement Learning","created":"2024-07-11","cited_by_count":1,"area":"deeprl"},{"id":"2502.13006","title":"Integrating Reinforcement Learning, Action Model Learning, and Numeric Planning for Tackling Complex Tasks","created":"2025-02-18","cited_by_count":1,"area":"offlinerl"},{"id":"2506.05968","title":"Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning","created":"2025-06-06","cited_by_count":1,"area":"deeprl"},{"id":"2604.11214","title":"HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning","created":"2026-04-13","cited_by_count":1,"area":"deeprl"},{"id":"2106.02943","title":"Learning Routines for Effective Off-Policy Reinforcement Learning","created":"2021-06-05","cited_by_count":0,"area":null},{"id":"2203.00251","title":"A Versatile Agent for Fast Learning from Human Instructors","created":"2022-03-01","cited_by_count":0,"area":null},{"id":"2212.12786","title":"SHIRO: Soft Hierarchical Reinforcement Learning","created":"2022-12-24","cited_by_count":0,"area":null},{"id":"2310.18303","title":"Socially Cognizant Robotics for a Technology Enhanced Society","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2402.06023","title":"Decision Theory-Guided Deep Reinforcement Learning for Fast Learning","created":"2024-02-08","cited_by_count":0,"area":"deeprl"},{"id":"2402.10803","title":"Modelling crypto markets by multi-agent reinforcement learning","created":"2024-02-16","cited_by_count":0,"area":null},{"id":"2407.19142","title":"On the benefits of pixel-based hierarchical policies for task generalization","created":"2024-07-27","cited_by_count":0,"area":"deeprl"},{"id":"2409.01066","title":"Learning in Hybrid Active Inference Models","created":"2024-09-02","cited_by_count":0,"area":null},{"id":"2409.18633","title":"Reducing Diversity to Generate Hierarchical Archetypes","created":"2024-09-27","cited_by_count":0,"area":null},{"id":"2410.11262","title":"Unveiling Options with Neural Decomposition","created":"2024-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2411.02998","title":"Accelerating Task Generalisation with Multi-Level Skill Hierarchies","created":"2024-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2412.16970","title":"A Research Agenda for Usability and Generalisation in Reinforcement Learning","created":"2024-12-22","cited_by_count":0,"area":"deeprl"},{"id":"2507.08705","title":"elsciRL: Integrating Language Solutions into Reinforcement Learning Problem Settings","created":"2025-07-11","cited_by_count":0,"area":"lr"},{"id":"2510.24674","title":"Learning to Drive Safely with Hybrid Options","created":"2025-10-28","cited_by_count":0,"area":"deeprl"},{"id":"2601.23156","title":"Unsupervised Hierarchical Skill Discovery","created":"2026-01-30","cited_by_count":0,"area":"deeprl"},{"id":"2604.05730","title":"Controllable Image Generation with Composed Parallel Token Prediction","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.13757","title":"Rethinking AI Hardware: A Three-Layer Cognitive Architecture for Autonomous Agents","created":"2026-04-15","cited_by_count":0,"area":"lr"},{"id":"2605.01131","title":"Forager: a lightweight testbed for continual learning with partial observability in RL","created":"2026-05-01","cited_by_count":0,"area":"deeprl"},{"id":"2606.24010","title":"Safe and Generalizable Hierarchical Multi-Agent RL via Constraint Manifold Control","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":null}