{"total":157,"rows":[{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"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":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196,"area":"offlinerl"},{"id":"2103.06257","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","created":"2021-03-10","cited_by_count":176,"area":null},{"id":"1802.09564","title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","created":"2018-02-26","cited_by_count":126,"area":"offlinerl"},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114,"area":"driving"},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106,"area":"offlinerl"},{"id":"2207.00713","title":"q-Learning in Continuous Time","created":"2022-07-02","cited_by_count":91,"area":null},{"id":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77,"area":"offlinerl"},{"id":"2101.01993","title":"A Survey of Deep RL and IL for Autonomous Driving Policy Learning","created":"2021-01-06","cited_by_count":61,"area":"driving"},{"id":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","cited_by_count":44,"area":"offlinerl"},{"id":"2104.05632","title":"Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment","created":"2021-04-12","cited_by_count":42,"area":"wm"},{"id":"2104.10159","title":"MBRL-Lib: A Modular Library for Model-based Reinforcement Learning","created":"2021-04-20","cited_by_count":42,"area":null},{"id":"2107.08285","title":"Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences","created":"2021-07-17","cited_by_count":41,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2201.12417","title":"Why Should I Trust You, Bellman? The Bellman Error is a Poor Replacement for Value Error","created":"2022-01-28","cited_by_count":32,"area":null},{"id":"1906.03352","title":"Watch, Try, Learn: Meta-Learning from Demonstrations and Reward","created":"2019-06-07","cited_by_count":28,"area":"offlinerl"},{"id":"2506.17784","title":"AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction","created":"2025-06-21","cited_by_count":25,"area":"agents"},{"id":"2110.10149","title":"Continuous Control with Action Quantization from Demonstrations","created":"2021-10-19","cited_by_count":22,"area":null},{"id":"2106.03050","title":"Efficient Continuous Control with Double Actors and Regularized Critics","created":"2021-06-06","cited_by_count":21,"area":null},{"id":"2107.10400","title":"Species Distribution Modeling for Machine Learning Practitioners: A Review","created":"2021-07-03","cited_by_count":21,"area":null},{"id":"2210.11481","title":"Improving aircraft performance using machine learning: a review","created":"2022-10-20","cited_by_count":19,"area":null},{"id":"2210.11931","title":"Deep Reinforcement Learning for Inverse Inorganic Materials Design","created":"2022-10-21","cited_by_count":19,"area":null},{"id":"2211.02147","title":"A Survey on Reinforcement Learning in Aviation Applications","created":"2022-11-03","cited_by_count":19,"area":null},{"id":"2212.00824","title":"On-device Training: A First Overview on Existing Systems","created":"2022-12-01","cited_by_count":19,"area":null},{"id":"2302.13960","title":"Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition","created":"2023-02-27","cited_by_count":19,"area":null},{"id":"2302.04903","title":"AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfer","created":"2023-02-09","cited_by_count":18,"area":null},{"id":"2405.19014","title":"Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption","created":"2024-05-29","cited_by_count":18,"area":"deeprl"},{"id":"2108.10273","title":"Collect & Infer -- a fresh look at data-efficient Reinforcement Learning","created":"2021-08-23","cited_by_count":17,"area":null},{"id":"2502.02705","title":"Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning","created":"2025-02-04","cited_by_count":17,"area":null},{"id":"2108.07124","title":"Using Cyber Terrain in Reinforcement Learning for Penetration Testing","created":"2021-08-16","cited_by_count":16,"area":null},{"id":"2306.17750","title":"TD Convergence: An Optimization Perspective","created":"2023-06-30","cited_by_count":16,"area":null},{"id":"2404.06492","title":"Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective","created":"2024-04-09","cited_by_count":16,"area":"deeprl"},{"id":"2103.12726","title":"Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning","created":"2021-03-23","cited_by_count":15,"area":null},{"id":"2103.17258","title":"Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning","created":"2021-03-31","cited_by_count":15,"area":null},{"id":"2212.09010","title":"Risk-Sensitive Reinforcement Learning with Exponential Criteria","created":"2022-12-18","cited_by_count":15,"area":null},{"id":"2301.00519","title":"Holistic Network Virtualization and Pervasive Network Intelligence for 6G","created":"2023-01-02","cited_by_count":14,"area":null},{"id":"2107.08241","title":"High-Accuracy Model-Based Reinforcement Learning, a Survey","created":"2021-07-17","cited_by_count":13,"area":null},{"id":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13,"area":"deeprl"},{"id":"2211.06625","title":"CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimality","created":"2022-11-12","cited_by_count":12,"area":null},{"id":"2404.08828","title":"Hindsight PRIORs for Reward Learning from Human Preferences","created":"2024-04-12","cited_by_count":12,"area":"alignment"},{"id":"2110.04686","title":"Braxlines: Fast and Interactive Toolkit for RL-driven Behavior Engineering beyond Reward Maximization","created":"2021-10-10","cited_by_count":11,"area":null},{"id":"2110.10349","title":"Distributed Reinforcement Learning for Privacy-Preserving Dynamic Edge Caching","created":"2021-10-20","cited_by_count":10,"area":null},{"id":"2310.18247","title":"Guided Data Augmentation for Offline Reinforcement Learning and Imitation Learning","created":"2023-10-27","cited_by_count":10,"area":"offlinerl"},{"id":"2107.00140","title":"Applications of the Free Energy Principle to Machine Learning and Neuroscience","created":"2021-06-30","cited_by_count":9,"area":null},{"id":"2108.07041","title":"Implicitly Regularized RL with Implicit Q-Values","created":"2021-08-16","cited_by_count":9,"area":null},{"id":"2109.13446","title":"Runtime Safety Assurance for Learning-enabled Control of Autonomous Driving Vehicles","created":"2021-09-28","cited_by_count":9,"area":"driving"},{"id":"2112.03798","title":"PTR-PPO: Proximal Policy Optimization with Prioritized Trajectory Replay","created":"2021-12-07","cited_by_count":9,"area":null},{"id":"2201.05000","title":"Automated Reinforcement Learning: An Overview","created":"2022-01-13","cited_by_count":9,"area":null},{"id":"2402.01344","title":"Monotone, Bi-Lipschitz, and Polyak-Lojasiewicz Networks","created":"2024-02-02","cited_by_count":9,"area":null},{"id":"2404.14238","title":"Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research Trajectories","created":"2024-04-22","cited_by_count":9,"area":"deeprl"},{"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":"1808.07903","title":"LIFT: Reinforcement Learning in Computer Systems by Learning From Demonstrations","created":"2018-08-23","cited_by_count":8,"area":"offlinerl"},{"id":"2110.02414","title":"Imaginary Hindsight Experience Replay: Curious Model-based Learning for Sparse Reward Tasks","created":"2021-10-05","cited_by_count":8,"area":null},{"id":"2106.04075","title":"Multi-Agent Cooperative Bidding Games for Multi-Objective Optimization in e-Commercial Sponsored Search","created":"2021-06-08","cited_by_count":7,"area":null},{"id":"2204.04558","title":"Gradient-Based Trajectory Optimization With Learned Dynamics","created":"2022-04-09","cited_by_count":7,"area":null},{"id":"2310.17786","title":"Understanding when Dynamics-Invariant Data Augmentations Benefit Model-Free Reinforcement Learning Updates","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2110.01954","title":"Continuous-Time Fitted Value Iteration for Robust Policies","created":"2021-10-05","cited_by_count":6,"area":null},{"id":"2112.11216","title":"Value Activation for Bias Alleviation: Generalized-activated Deep Double Deterministic Policy Gradients","created":"2021-12-21","cited_by_count":6,"area":null},{"id":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"id":"2104.01036","title":"Hybrid Policy Learning for Energy-Latency Tradeoff in MEC-Assisted VR Video Service","created":"2021-04-02","cited_by_count":5,"area":null},{"id":"2209.13126","title":"Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter","created":"2022-09-27","cited_by_count":5,"area":null},{"id":"2306.07552","title":"Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second","created":"2023-06-13","cited_by_count":5,"area":null},{"id":"2404.00340","title":"Deep Reinforcement Learning in Autonomous Car Path Planning and Control: A Survey","created":"2024-03-30","cited_by_count":5,"area":"deeprl"},{"id":"2407.15537","title":"Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints","created":"2024-07-22","cited_by_count":5,"area":"deeprl"},{"id":"2509.00215","title":"First Order Model-Based RL through Decoupled Backpropagation","created":"2025-08-29","cited_by_count":5,"area":"deeprl"},{"id":"2510.26270","title":"Graph-Enhanced Policy Optimization in LLM Agent Training","created":"2025-10-30","cited_by_count":5,"area":"agents"},{"id":"2602.05031","title":"Laplacian Representations for Decision-Time Planning","created":"2026-02-04","cited_by_count":5,"area":"deeprl"},{"id":"2101.09933","title":"A Survey on Active Deep Learning: From Model-driven to Data-driven","created":"2021-01-25","cited_by_count":4,"area":null},{"id":"2103.10245","title":"Building Safer Autonomous Agents by Leveraging Risky Driving Behavior Knowledge","created":"2021-03-16","cited_by_count":4,"area":"driving"},{"id":"2104.04080","title":"Design and implementation of an environment for Learning to Run a Power Network (L2RPN)","created":"2021-04-06","cited_by_count":4,"area":null},{"id":"2408.00309","title":"Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning","created":"2024-08-01","cited_by_count":4,"area":"deeprl"},{"id":"2410.03924","title":"Online Control-Informed Learning","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2412.14312","title":"Stealing That Free Lunch: Exposing the Limits of Dyna-Style Reinforcement Learning","created":"2024-12-18","cited_by_count":4,"area":"deeprl"},{"id":"2510.17122","title":"Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control","created":"2025-10-20","cited_by_count":4,"area":"deeprl"},{"id":"2106.12194","title":"Uncertainty-Aware Model-Based Reinforcement Learning with Application to Autonomous Driving","created":"2021-06-23","cited_by_count":3,"area":"driving"},{"id":"2111.12197","title":"Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS","created":"2021-11-23","cited_by_count":3,"area":null},{"id":"2208.12136","title":"A Comparison of Reinforcement Learning Frameworks for Software Testing Tasks","created":"2022-08-25","cited_by_count":3,"area":null},{"id":"2212.01343","title":"CT-DQN: Control-Tutored Deep Reinforcement Learning","created":"2022-12-02","cited_by_count":3,"area":null},{"id":"2309.04615","title":"VDFD: Multi-Agent Value Decomposition Framework with Disentangled World Model","created":"2023-09-08","cited_by_count":3,"area":"wm"},{"id":"2402.18016","title":"User Decision Guidance with Selective Explanation Presentation from Explainable-AI","created":"2024-02-28","cited_by_count":3,"area":null},{"id":"2403.04162","title":"Noisy Spiking Actor Network for Exploration","created":"2024-03-07","cited_by_count":3,"area":"deeprl"},{"id":"2410.03915","title":"Distribution Guided Active Feature Acquisition","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2410.04988","title":"Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling","created":"2024-10-07","cited_by_count":3,"area":"deeprl"},{"id":"2410.11833","title":"Mitigating Suboptimality of Deterministic Policy Gradients in Complex Q-functions","created":"2024-10-15","cited_by_count":3,"area":"deeprl"},{"id":"2503.20139","title":"Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learning","created":"2025-03-26","cited_by_count":3,"area":"deeprl"},{"id":"2109.01768","title":"Eden: A Unified Environment Framework for Booming Reinforcement Learning Algorithms","created":"2021-09-04","cited_by_count":2,"area":null},{"id":"2205.12770","title":"An Experimental Comparison Between Temporal Difference and Residual Gradient with Neural Network Approximation","created":"2022-05-25","cited_by_count":2,"area":null},{"id":"2206.10249","title":"Incorporating Voice Instructions in Model-Based Reinforcement Learning for Self-Driving Cars","created":"2022-06-21","cited_by_count":2,"area":"driving"},{"id":"2304.10590","title":"A Review of Symbolic, Subsymbolic and Hybrid Methods for Sequential Decision Making","created":"2023-04-20","cited_by_count":2,"area":null},{"id":"2310.13230","title":"Absolute Policy Optimization","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2408.07245","title":"q-exponential family for policy optimization","created":"2024-08-14","cited_by_count":2,"area":"deeprl"},{"id":"2411.14991","title":"Free Energy Projective Simulation (FEPS): Active inference with interpretability","created":"2024-11-22","cited_by_count":2,"area":null},{"id":"2602.05965","title":"Learning to Share: Selective Memory for Efficient Parallel Agentic Systems","created":"2026-02-05","cited_by_count":2,"area":"agents"},{"id":"2608.17163","title":"Q-Learning With World Models","created":"2026-08-17","cited_by_count":2,"area":"wm"},{"id":"2103.14256","title":"Learning Reactive and Predictive Differentiable Controllers for Switching Linear Dynamical Models","created":"2021-03-26","cited_by_count":1,"area":null},{"id":"2104.10403","title":"Model-aided Deep Reinforcement Learning for Sample-efficient UAV Trajectory Design in IoT Networks","created":"2021-04-21","cited_by_count":1,"area":null},{"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}],"next_cursor":"100"}