{"total":72,"rows":[{"id":"2102.02915","title":"How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned","created":"2021-02-04","cited_by_count":213,"area":null},{"id":"2106.12534","title":"Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisation","created":"2021-06-23","cited_by_count":122,"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":"2104.11213","title":"ManipulaTHOR: A Framework for Visual Object Manipulation","created":"2021-04-22","cited_by_count":102,"area":null},{"id":"2106.13105","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","created":"2021-06-24","cited_by_count":67,"area":null},{"id":"2207.00429","title":"Modular Lifelong Reinforcement Learning via Neural Composition","created":"2022-07-01","cited_by_count":40,"area":null},{"id":"2110.04276","title":"Offline Meta-Reinforcement Learning for Industrial Insertion","created":"2021-10-08","cited_by_count":39,"area":"offlinerl"},{"id":"2402.12343","title":"Emulated Disalignment: Safety Alignment for Large Language Models May Backfire!","created":"2024-02-19","cited_by_count":37,"area":"alignment"},{"id":"2105.07142","title":"Move2Hear: Active Audio-Visual Source Separation","created":"2021-05-15","cited_by_count":35,"area":null},{"id":"2101.07012","title":"Regularized Policies are Reward Robust","created":"2021-01-18","cited_by_count":32,"area":null},{"id":"2103.13842","title":"Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning","created":"2021-03-25","cited_by_count":28,"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":"2201.00042","title":"Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments","created":"2021-12-31","cited_by_count":25,"area":null},{"id":"2406.14235","title":"Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation","created":"2024-06-20","cited_by_count":23,"area":null},{"id":"2207.04136","title":"CompoSuite: A Compositional Reinforcement Learning Benchmark","created":"2022-07-08","cited_by_count":21,"area":null},{"id":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","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":"2105.04962","title":"Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning","created":"2021-05-11","cited_by_count":16,"area":null},{"id":"2204.01571","title":"Coarse-to-Fine Q-attention with Learned Path Ranking","created":"2022-04-04","cited_by_count":13,"area":null},{"id":"2112.02852","title":"Target Entropy Annealing for Discrete Soft Actor-Critic","created":"2021-12-06","cited_by_count":10,"area":null},{"id":"2204.12471","title":"Coarse-to-fine Q-attention with Tree Expansion","created":"2022-04-26","cited_by_count":9,"area":null},{"id":"2205.12532","title":"Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning","created":"2022-05-25","cited_by_count":9,"area":null},{"id":"2212.01174","title":"Utilizing Prior Solutions for Reward Shaping and Composition in Entropy-Regularized Reinforcement Learning","created":"2022-12-02","cited_by_count":8,"area":null},{"id":"2310.00435","title":"Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards","created":"2023-09-30","cited_by_count":8,"area":null},{"id":"2503.17338","title":"Capturing Individual Human Preferences with Reward Features","created":"2025-03-21","cited_by_count":8,"area":"alignment"},{"id":"2209.15205","title":"ASPiRe:Adaptive Skill Priors for Reinforcement Learning","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2301.12305","title":"Composing Task Knowledge with Modular Successor Feature Approximators","created":"2023-01-28","cited_by_count":7,"area":null},{"id":"2106.15380","title":"Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes","created":"2021-06-29","cited_by_count":6,"area":null},{"id":"2108.02439","title":"Learning to Design and Construct Bridge without Blueprint","created":"2021-08-05","cited_by_count":6,"area":null},{"id":"2302.02182","title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","created":"2023-02-04","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":"2402.09992","title":"Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts","created":"2024-02-15","cited_by_count":6,"area":"deeprl"},{"id":"2501.09080","title":"Average-Reward Soft Actor-Critic","created":"2025-01-15","cited_by_count":6,"area":"deeprl"},{"id":"2210.00350","title":"Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning","created":"2022-10-01","cited_by_count":5,"area":null},{"id":"2310.02360","title":"Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2409.19816","title":"Grounded Curriculum Learning","created":"2024-09-29","cited_by_count":5,"area":"deeprl"},{"id":"2406.18033","title":"Boosting Soft Q-Learning by Bounding","created":"2024-06-26","cited_by_count":4,"area":"deeprl"},{"id":"2110.03032","title":"Learning Multi-Objective Curricula for Robotic Policy Learning","created":"2021-10-06","cited_by_count":3,"area":null},{"id":"2110.04647","title":"Learning to Follow Language Instructions with Compositional Policies","created":"2021-10-09","cited_by_count":3,"area":null},{"id":"2303.02557","title":"Bounding the Optimal Value Function in Compositional Reinforcement Learning","created":"2023-03-05","cited_by_count":3,"area":null},{"id":"2307.16062","title":"Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning","created":"2023-07-29","cited_by_count":3,"area":null},{"id":"2412.06655","title":"Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures","created":"2024-12-09","cited_by_count":3,"area":"deeprl"},{"id":"2508.02988","title":"GACL: Grounded Adaptive Curriculum Learning with Active Task and Performance Monitoring","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2107.04457","title":"Aligning an optical interferometer with beam divergence control and continuous action space","created":"2021-07-09","cited_by_count":2,"area":null},{"id":"2204.05509","title":"Learning Design and Construction with Varying-Sized Materials via Prioritized Memory Resets","created":"2022-04-12","cited_by_count":2,"area":null},{"id":"2208.08790","title":"Explainable Reinforcement Learning on Financial Stock Trading using SHAP","created":"2022-08-18","cited_by_count":2,"area":null},{"id":"2301.13450","title":"Learning Vision-based Robotic Manipulation Tasks Sequentially in Offline Reinforcement Learning Settings","created":"2023-01-31","cited_by_count":2,"area":"offlinerl"},{"id":"2410.03892","title":"Towards Cost Sensitive Decision Making","created":"2024-10-04","cited_by_count":2,"area":null},{"id":"2102.04775","title":"Structured Diversification Emergence via Reinforced Organization Control and Hierarchical Consensus Learning","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2103.06617","title":"A Quadratic Actor Network for Model-Free Reinforcement Learning","created":"2021-03-11","cited_by_count":1,"area":null},{"id":"2108.10533","title":"Entropy-Aware Model Initialization for Effective Exploration in Deep Reinforcement Learning","created":"2021-08-24","cited_by_count":1,"area":null},{"id":"2204.08573","title":"Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models","created":"2022-04-18","cited_by_count":1,"area":null},{"id":"2205.13441","title":"Multi-Phase Multi-Objective Dexterous Manipulation with Adaptive Hierarchical Curriculum","created":"2022-05-26","cited_by_count":1,"area":null},{"id":"2301.05346","title":"A Constrained-Optimization Approach to the Execution of Prioritized Stacks of Learned Multi-Robot Tasks","created":"2023-01-13","cited_by_count":1,"area":null},{"id":"2309.13955","title":"Deep Reinforcement Learning for the Heat Transfer Control of Pulsating Impinging Jets","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2409.20016","title":"Dynamic Policy Fusion for User Alignment Without Re-Interaction","created":"2024-09-30","cited_by_count":1,"area":"alignment"},{"id":"2506.10871","title":"Viability of Future Actions: Robust Safety in Reinforcement Learning via Entropy Regularization","created":"2025-06-12","cited_by_count":1,"area":"deeprl"},{"id":"2602.10635","title":"OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2202.02395","title":"Malleable Agents for Re-Configurable Robotic Manipulators","created":"2022-02-04","cited_by_count":0,"area":null},{"id":"2209.09536","title":"Towards Task-Prioritized Policy Composition","created":"2022-09-20","cited_by_count":0,"area":null},{"id":"2302.09676","title":"Leveraging Prior Knowledge in Reinforcement Learning via Double-Sided Bounds on the Value Function","created":"2023-02-19","cited_by_count":0,"area":null},{"id":"2310.07493","title":"Diversity for Contingency: Learning Diverse Behaviors for Efficient Adaptation and Transfer","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2404.19070","title":"Reinforcement Learning Driven Cooperative Ball Balance in Rigidly Coupled Drones","created":"2024-04-29","cited_by_count":0,"area":"deeprl"},{"id":"2406.07069","title":"Optimal Gait Control for a Tendon-driven Soft Quadruped Robot by Model-based Reinforcement Learning","created":"2024-06-11","cited_by_count":0,"area":"deeprl"},{"id":"2501.12539","title":"Compositional Instruction Following with Language Models and Reinforcement Learning","created":"2025-01-21","cited_by_count":0,"area":null},{"id":"2504.01174","title":"Value Iteration for Learning Concurrently Executable Robotic Control Tasks","created":"2025-04-01","cited_by_count":0,"area":null},{"id":"2604.22873","title":"When Policies Cannot Be Retrained: A Unified Closed-Form View of Post-Training Steering in Offline Reinforcement Learning","created":"2026-04-23","cited_by_count":0,"area":"offlinerl"},{"id":"2606.02251","title":"FW-NKF: Frequency-Weighted Neural Kalman Filters","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.04053","title":"A Goal-Set Characterization of Task Composition in the Boolean Task Algebra","created":"2026-06-02","cited_by_count":0,"area":"deeprl"},{"id":"2607.17316","title":"Rationalizing Boltzmann Rationality: An Axiomatic Characterization of Entropy-Regularized Policies","created":"2026-07-19","cited_by_count":0,"area":"deeprl"},{"id":"2608.07180","title":"Momba: Network Modernization Improves Multi-Objective Reinforcement Learning","created":"2026-08-07","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}