{"total":70,"rows":[{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571,"area":"alignment"},{"id":"2306.08647","title":"Language to Rewards for Robotic Skill Synthesis","created":"2023-06-14","cited_by_count":312,"area":"lr"},{"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":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176,"area":"deeprl"},{"id":"2107.05612","title":"A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution","created":"2021-07-12","cited_by_count":91,"area":null},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70,"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":"2102.13651","title":"On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning","created":"2021-02-26","cited_by_count":59,"area":null},{"id":"2306.16740","title":"Principles and Guidelines for Evaluating Social Robot Navigation Algorithms","created":"2023-06-29","cited_by_count":56,"area":null},{"id":"2112.02094","title":"Coupling Vision and Proprioception for Navigation of Legged Robots","created":"2021-12-03","cited_by_count":51,"area":null},{"id":"2103.04351","title":"Learning a State Representation and Navigation in Cluttered and Dynamic Environments","created":"2021-03-07","cited_by_count":41,"area":null},{"id":"2203.07060","title":"MotionSC: Data Set and Network for Real-Time Semantic Mapping in Dynamic Environments","created":"2022-03-14","cited_by_count":40,"area":"wm"},{"id":"2309.06687","title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics","created":"2023-09-13","cited_by_count":36,"area":null},{"id":"2205.13536","title":"Verifying Learning-Based Robotic Navigation Systems","created":"2022-05-26","cited_by_count":33,"area":null},{"id":"2203.12071","title":"WayFAST: Navigation with Predictive Traversability in the Field","created":"2022-03-22","cited_by_count":32,"area":null},{"id":"2209.10780","title":"Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation","created":"2022-09-22","cited_by_count":29,"area":null},{"id":"2303.04150","title":"Evolutionary Reinforcement Learning: A Survey","created":"2023-03-07","cited_by_count":29,"area":null},{"id":"2209.08890","title":"An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey","created":"2022-09-19","cited_by_count":28,"area":null},{"id":"2103.13834","title":"Self-Imitation Learning by Planning","created":"2021-03-25","cited_by_count":26,"area":"offlinerl"},{"id":"2203.15983","title":"VI-IKD: High-Speed Accurate Off-Road Navigation using Learned Visual-Inertial Inverse Kinodynamics","created":"2022-03-30","cited_by_count":21,"area":null},{"id":"2210.04839","title":"Benchmarking Reinforcement Learning Techniques for Autonomous Navigation","created":"2022-10-10","cited_by_count":19,"area":null},{"id":"2109.08968","title":"Visual Representation Learning for Preference-Aware Path Planning","created":"2021-09-18","cited_by_count":18,"area":null},{"id":"2207.13676","title":"Open Source Vizier: Distributed Infrastructure and API for Reliable and Flexible Blackbox Optimization","created":"2022-07-27","cited_by_count":18,"area":null},{"id":"2409.14972","title":"Deep Reinforcement Learning-based Obstacle Avoidance for Robot Movement in Warehouse Environments","created":"2024-09-23","cited_by_count":17,"area":"deeprl"},{"id":"2104.03111","title":"Risk-Conditioned Distributional Soft Actor-Critic for Risk-Sensitive Navigation","created":"2021-04-07","cited_by_count":15,"area":null},{"id":"2104.03616","title":"Arena-Rosnav: Towards Deployment of Deep-Reinforcement-Learning-Based Obstacle Avoidance into Conventional Autonomous Navigation Systems","created":"2021-04-08","cited_by_count":15,"area":null},{"id":"2109.00525","title":"Catastrophic Interference in Reinforcement Learning: A Solution Based on Context Division and Knowledge Distillation","created":"2021-09-01","cited_by_count":15,"area":"distill"},{"id":"2009.14509","title":"Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning","created":"2020-09-30","cited_by_count":14,"area":"offlinerl"},{"id":"2209.00347","title":"Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization","created":"2022-09-01","cited_by_count":14,"area":null},{"id":"1909.12971","title":"Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation","created":"2019-09-27","cited_by_count":13,"area":"offlinerl"},{"id":"2411.02547","title":"Modeling Uncertainty in 3D Gaussian Splatting through Continuous Semantic Splatting","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2206.08487","title":"High-Speed Accurate Robot Control using Learned Forward Kinodynamics and Non-linear Least Squares Optimization","created":"2022-06-16","cited_by_count":11,"area":null},{"id":"2201.05000","title":"Automated Reinforcement Learning: An Overview","created":"2022-01-13","cited_by_count":9,"area":null},{"id":"2302.10030","title":"Safe Deep Reinforcement Learning by Verifying Task-Level Properties","created":"2023-02-20","cited_by_count":9,"area":null},{"id":"2106.15883","title":"Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL","created":"2021-06-30","cited_by_count":8,"area":null},{"id":"2406.10540","title":"Generating and Evolving Reward Functions for Highway Driving with Large Language Models","created":"2024-06-15","cited_by_count":8,"area":"driving"},{"id":"2402.05284","title":"Analyzing Adversarial Inputs in Deep Reinforcement Learning","created":"2024-02-07","cited_by_count":7,"area":"deeprl"},{"id":"2502.01616","title":"Preference VLM: Leveraging VLMs for Scalable Preference-Based Reinforcement Learning","created":"2025-02-03","cited_by_count":7,"area":"alignment"},{"id":"2104.03663","title":"Connecting Deep-Reinforcement-Learning-based Obstacle Avoidance with Conventional Global Planners using Waypoint Generators","created":"2021-04-08","cited_by_count":6,"area":null},{"id":"2105.10396","title":"Language Understanding for Field and Service Robots in a Priori Unknown Environments","created":"2021-05-21","cited_by_count":6,"area":null},{"id":"2111.12673","title":"Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning","created":"2021-11-24","cited_by_count":6,"area":null},{"id":"2203.01190","title":"Model-free Neural Lyapunov Control for Safe Robot Navigation","created":"2022-03-02","cited_by_count":6,"area":null},{"id":"2210.01162","title":"Learning Minimally-Violating Continuous Control for Infeasible Linear Temporal Logic Specifications","created":"2022-10-03","cited_by_count":6,"area":null},{"id":"2502.17813","title":"Safe Multi-Agent Navigation guided by Goal-Conditioned Safe Reinforcement Learning","created":"2025-02-25","cited_by_count":6,"area":null},{"id":"2109.11288","title":"Enhancing Navigational Safety in Crowded Environments using Semantic-Deep-Reinforcement-Learning-based Navigation","created":"2021-09-23","cited_by_count":5,"area":null},{"id":"2203.02230","title":"Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning","created":"2022-03-04","cited_by_count":5,"area":null},{"id":"2506.00276","title":"RoboMoRe: LLM-based Robot Co-design via Joint Optimization of Morphology and Reward","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2108.03180","title":"Dynamic Semantic Occupancy Mapping using 3D Scene Flow and Closed-Form Bayesian Inference","created":"2021-08-06","cited_by_count":4,"area":null},{"id":"2306.06754","title":"Reinforcement Learning in Robotic Motion Planning by Combined Experience-based Planning and Self-Imitation Learning","created":"2023-06-11","cited_by_count":4,"area":"offlinerl"},{"id":"2106.13280","title":"Hierarchically Integrated Models: Learning to Navigate from Heterogeneous Robots","created":"2021-06-24","cited_by_count":3,"area":null},{"id":"2309.02632","title":"Deep Reinforcement Learning from Hierarchical Preference Design","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2606.01672","title":"RDA: Reward Design Agent for Reinforcement Learning","created":"2026-06-01","cited_by_count":3,"area":"agents"},{"id":"2302.02921","title":"Holistic Deep-Reinforcement-Learning-based Training of Autonomous Navigation Systems","created":"2023-02-06","cited_by_count":2,"area":null},{"id":"2309.13266","title":"Robust Navigation with Cross-Modal Fusion and Knowledge Transfer","created":"2023-09-23","cited_by_count":2,"area":"distill"},{"id":"2407.06056","title":"Stranger Danger! Identifying and Avoiding Unpredictable Pedestrians in RL-based Social Robot Navigation","created":"2024-07-08","cited_by_count":2,"area":"deeprl"},{"id":"2410.11783","title":"LatentBKI: Open-Dictionary Continuous Mapping in Visual-Language Latent Spaces with Quantifiable Uncertainty","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2204.04292","title":"Evolving Pareto-Optimal Actor-Critic Algorithms for Generalizability and Stability","created":"2022-04-08","cited_by_count":1,"area":null},{"id":"2301.05980","title":"Deep-Reinforcement-Learning-based Path Planning for Industrial Robots using Distance Sensors as Observation","created":"2023-01-14","cited_by_count":1,"area":null},{"id":"2302.02898","title":"Arena-Web -- A Web-based Development and Benchmarking Platform for Autonomous Navigation Approaches","created":"2023-02-06","cited_by_count":1,"area":null},{"id":"2306.08870","title":"Evolutionary Curriculum Training for DRL-Based Navigation Systems","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2504.19480","title":"An Automated Reinforcement Learning Reward Design Framework with Large Language Model for Cooperative Platoon Coordination","created":"2025-04-28","cited_by_count":1,"area":null},{"id":"2509.08157","title":"Risk-Bounded Multi-Agent Visual Navigation via Iterative Risk Allocation","created":"2025-09-09","cited_by_count":1,"area":null},{"id":"2603.28053","title":"Reducing Oracle Feedback with Vision-Language Embeddings for Preference-Based RL","created":"2026-03-30","cited_by_count":1,"area":"deeprl"},{"id":"2103.05343","title":"A model-based framework for learning transparent swarm behaviors","created":"2021-03-09","cited_by_count":0,"area":null},{"id":"2210.08280","title":"Robot Navigation Anticipative Strategies in Deep Reinforcement Motion Planning","created":"2022-10-15","cited_by_count":0,"area":null},{"id":"2306.06192","title":"Confidence-Controlled Exploration: Efficient Sparse-Reward Policy Learning for Robot Navigation","created":"2023-06-09","cited_by_count":0,"area":null},{"id":"2308.14652","title":"Learning Visual Tracking and Reaching with Deep Reinforcement Learning on a UR10e Robotic Arm","created":"2023-08-28","cited_by_count":0,"area":null},{"id":"2512.05320","title":"Enhancing Deep Deterministic Policy Gradients on Continuous Control Tasks with Decoupled Prioritized Experience Replay","created":"2025-12-04","cited_by_count":0,"area":"deeprl"},{"id":"2605.00059","title":"Dynamic-TD3: A Novel Algorithm for UAV Path Planning with Dynamic Obstacle Trajectory Prediction","created":"2026-04-30","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}