{"total":123,"rows":[{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807,"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":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170,"area":null},{"id":"2105.00636","title":"Learning to drive from a world on rails","created":"2021-05-03","cited_by_count":114,"area":"driving"},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109,"area":null},{"id":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93,"area":null},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82,"area":null},{"id":"2102.03479","title":"Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning","created":"2021-02-06","cited_by_count":68,"area":null},{"id":"2104.03113","title":"Scaling Scaling Laws with Board Games","created":"2021-04-07","cited_by_count":63,"area":null},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53,"area":null},{"id":"2202.10324","title":"VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learning","created":"2022-02-17","cited_by_count":52,"area":null},{"id":"2502.07825","title":"Pre-Trained Video Generative Models as World Simulators","created":"2025-02-10","cited_by_count":44,"area":null},{"id":"2301.13442","title":"Scaling laws for single-agent reinforcement learning","created":"2023-01-31","cited_by_count":41,"area":null},{"id":"2205.12258","title":"History Compression via Language Models in Reinforcement Learning","created":"2022-05-24","cited_by_count":39,"area":null},{"id":"2309.06553","title":"Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL","created":"2023-09-13","cited_by_count":37,"area":"lr"},{"id":"2104.01655","title":"Efficient Transformers in Reinforcement Learning using Actor-Learner Distillation","created":"2021-04-04","cited_by_count":35,"area":null},{"id":"2110.00641","title":"Batch size-invariance for policy optimization","created":"2021-10-01","cited_by_count":35,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2207.00986","title":"Stabilizing Off-Policy Deep Reinforcement Learning from Pixels","created":"2022-07-03","cited_by_count":32,"area":null},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31,"area":"wm"},{"id":"2401.11963","title":"Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms","created":"2024-01-22","cited_by_count":26,"area":"deeprl"},{"id":"2210.01542","title":"Hyperbolic Deep Reinforcement Learning","created":"2022-10-04","cited_by_count":25,"area":null},{"id":"2103.15332","title":"Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark","created":"2021-03-29","cited_by_count":23,"area":null},{"id":"2106.02193","title":"Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL","created":"2021-06-04","cited_by_count":20,"area":null},{"id":"2206.12984","title":"Improving Policy Optimization with Generalist-Specialist Learning","created":"2022-06-26","cited_by_count":20,"area":null},{"id":"2306.03072","title":"Explore to Generalize in Zero-Shot RL","created":"2023-06-05","cited_by_count":20,"area":null},{"id":"2303.02430","title":"CFlowNets: Continuous Control with Generative Flow Networks","created":"2023-03-04","cited_by_count":19,"area":"diffusion"},{"id":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17,"area":"deeprl"},{"id":"2409.04792","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","created":"2024-09-07","cited_by_count":17,"area":"deeprl"},{"id":"2206.12030","title":"Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning","created":"2022-06-24","cited_by_count":16,"area":null},{"id":"2211.02100","title":"Contrastive Value Learning: Implicit Models for Simple Offline RL","created":"2022-11-03","cited_by_count":15,"area":"offlinerl"},{"id":"2507.19672","title":"Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges","created":"2025-07-25","cited_by_count":15,"area":"alignment"},{"id":"2206.02126","title":"Learning Dynamics and Generalization in Reinforcement Learning","created":"2022-06-05","cited_by_count":14,"area":null},{"id":"2210.17375","title":"ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation","created":"2022-10-26","cited_by_count":14,"area":null},{"id":"2502.08938","title":"Reevaluating Policy Gradient Methods for Imperfect-Information Games","created":"2025-02-13","cited_by_count":13,"area":"deeprl"},{"id":"2507.03298","title":"Dyn-O: Building Structured World Models with Object-Centric Representations","created":"2025-07-04","cited_by_count":13,"area":"wm"},{"id":"2407.11070","title":"Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Search","created":"2024-07-12","cited_by_count":12,"area":null},{"id":"2209.14940","title":"Reinforcement Learning Algorithms: An Overview and Classification","created":"2022-09-29","cited_by_count":10,"area":null},{"id":"2309.10790","title":"Guide Your Agent with Adaptive Multimodal Rewards","created":"2023-09-19","cited_by_count":10,"area":"offlinerl"},{"id":"2103.05147","title":"Model-free Policy Learning with Reward Gradients","created":"2021-03-09","cited_by_count":9,"area":null},{"id":"2306.13284","title":"Correcting discount-factor mismatch in on-policy policy gradient methods","created":"2023-06-23","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":"2210.09960","title":"Rethinking Value Function Learning for Generalization in Reinforcement Learning","created":"2022-10-18","cited_by_count":8,"area":null},{"id":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","cited_by_count":8,"area":"deeprl"},{"id":"2503.06343","title":"Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learning","created":"2025-03-08","cited_by_count":8,"area":"deeprl"},{"id":"2304.10770","title":"DEIR: Efficient and Robust Exploration through Discriminative-Model-Based Episodic Intrinsic Rewards","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2310.17805","title":"Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2411.03820","title":"Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC","created":"2024-11-06","cited_by_count":7,"area":"deeprl"},{"id":"2507.11019","title":"Relative Entropy Pathwise Policy Optimization","created":"2025-07-15","cited_by_count":7,"area":"deeprl"},{"id":"2602.16229","title":"Factored Latent Action World Models","created":"2026-02-18","cited_by_count":7,"area":"wm"},{"id":"2108.02439","title":"Learning to Design and Construct Bridge without Blueprint","created":"2021-08-05","cited_by_count":6,"area":null},{"id":"2208.12328","title":"Autonomous Unmanned Aerial Vehicle Navigation using Reinforcement Learning: A Systematic Review","created":"2022-08-25","cited_by_count":6,"area":null},{"id":"2209.07288","title":"Optimistic Curiosity Exploration and Conservative Exploitation with Linear Reward Shaping","created":"2022-09-15","cited_by_count":6,"area":"offlinerl"},{"id":"2307.03486","title":"Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning","created":"2023-07-07","cited_by_count":6,"area":null},{"id":"2406.01853","title":"Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2410.10905","title":"Improving Generalization on the ProcGen Benchmark with Simple Architectural Changes and Scale","created":"2024-10-13","cited_by_count":6,"area":"deeprl"},{"id":"2312.08365","title":"An Invitation to Deep Reinforcement Learning","created":"2023-12-13","cited_by_count":5,"area":null},{"id":"2401.13662","title":"The Definitive Guide to Policy Gradients in Deep Reinforcement Learning: Theory, Algorithms and Implementations","created":"2024-01-24","cited_by_count":5,"area":"deeprl"},{"id":"2505.19247","title":"Improving Value Estimation Critically Enhances Vanilla Policy Gradient","created":"2025-05-25","cited_by_count":5,"area":"deeprl"},{"id":"2604.15590","title":"CSLE: A Reinforcement Learning Platform for Autonomous Security Management","created":"2026-04-16","cited_by_count":5,"area":"deeprl"},{"id":"2207.06105","title":"GriddlyJS: A Web IDE for Reinforcement Learning","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2106.05332","title":"Reinforcement Learning for Industrial Control Network Cyber Security Orchestration","created":"2021-06-09","cited_by_count":3,"area":null},{"id":"2201.09568","title":"Pearl: Parallel Evolutionary and Reinforcement Learning Library","created":"2022-01-24","cited_by_count":3,"area":null},{"id":"2309.16382","title":"RLLTE: Long-Term Evolution Project of Reinforcement Learning","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2406.02890","title":"Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning","created":"2024-06-05","cited_by_count":3,"area":null},{"id":"2504.05152","title":"PanoDreamer: Consistent Text to 360-Degree Scene Generation","created":"2025-04-07","cited_by_count":3,"area":null},{"id":"2512.14202","title":"Understanding and Improving Hyperbolic Deep Reinforcement Learning","created":"2025-12-16","cited_by_count":3,"area":"deeprl"},{"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":"2206.10027","title":"DNA: Proximal Policy Optimization with a Dual Network Architecture","created":"2022-06-20","cited_by_count":2,"area":null},{"id":"2210.06766","title":"Policy Gradient With Serial Markov Chain Reasoning","created":"2022-10-13","cited_by_count":2,"area":"lr"},{"id":"2309.12560","title":"Machine Learning Meets Advanced Robotic Manipulation","created":"2023-09-22","cited_by_count":2,"area":null},{"id":"2310.04796","title":"Accelerate Multi-Agent Reinforcement Learning in Zero-Sum Games with Subgame Curriculum Learning","created":"2023-10-07","cited_by_count":2,"area":null},{"id":"2312.03126","title":"Learning Curricula in Open-Ended Worlds","created":"2023-12-03","cited_by_count":2,"area":null},{"id":"2411.11318","title":"Syllabus: Portable Curricula for Reinforcement Learning Agents","created":"2024-11-18","cited_by_count":2,"area":"deeprl"},{"id":"2506.01261","title":"The Actor-Critic Update Order Matters for PPO in Federated Reinforcement Learning","created":"2025-06-02","cited_by_count":2,"area":"deeprl"},{"id":"2105.03923","title":"CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration","created":"2021-05-09","cited_by_count":1,"area":null},{"id":"2106.13037","title":"Mix and Mask Actor-Critic Methods","created":"2021-06-24","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":"2209.14488","title":"Ensemble Reinforcement Learning in Continuous Spaces -- A Hierarchical Multi-Step Approach for Policy Training","created":"2022-09-29","cited_by_count":1,"area":null},{"id":"2301.08442","title":"Revisiting Estimation Bias in Policy Gradients for Deep Reinforcement Learning","created":"2023-01-20","cited_by_count":1,"area":null},{"id":"2304.09825","title":"Using Offline Data to Speed Up Reinforcement Learning in Procedurally Generated Environments","created":"2023-04-18","cited_by_count":1,"area":"offlinerl"},{"id":"2305.04361","title":"Truncating Trajectories in Monte Carlo Reinforcement Learning","created":"2023-05-07","cited_by_count":1,"area":null},{"id":"2311.07312","title":"C-Procgen: Empowering Procgen with Controllable Contexts","created":"2023-11-13","cited_by_count":1,"area":null},{"id":"2312.05405","title":"Guaranteed Trust Region Optimization via Two-Phase KL Penalization","created":"2023-12-08","cited_by_count":1,"area":null},{"id":"2407.03426","title":"Multi-Task Decision-Making for Multi-User 360 Video Processing over Wireless Networks","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2410.13463","title":"Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach","created":"2024-10-17","cited_by_count":1,"area":"deeprl"},{"id":"2501.02481","title":"Representation Convergence: Mutual Distillation is Secretly a Form of Regularization","created":"2025-01-05","cited_by_count":1,"area":"deeprl"},{"id":"2501.12620","title":"Adaptive Data Exploitation in Deep Reinforcement Learning","created":"2025-01-22","cited_by_count":1,"area":"deeprl"},{"id":"2502.08336","title":"Salience-Invariant Consistent Policy Learning for Generalization in Visual Reinforcement Learning","created":"2025-02-12","cited_by_count":1,"area":"deeprl"},{"id":"2508.01329","title":"Is Exploration or Optimization the Problem for Deep Reinforcement Learning?","created":"2025-08-02","cited_by_count":1,"area":"deeprl"},{"id":"2508.03194","title":"Scaling DRL for Decision Making: A Survey on Data, Network, and Training Budget Strategies","created":"2025-08-05","cited_by_count":1,"area":null},{"id":"2509.05273","title":"Greener Deep Reinforcement Learning: Analysis of Energy and Carbon Efficiency Across Atari Benchmarks","created":"2025-09-05","cited_by_count":1,"area":"deeprl"},{"id":"2510.24194","title":"Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames","created":"2025-10-28","cited_by_count":1,"area":"offlinerl"},{"id":"2601.23075","title":"RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning","created":"2026-01-30","cited_by_count":1,"area":"deeprl"},{"id":"2606.29457","title":"How Much Due Diligence Before You Bid? Learning in Intractable Takeover Auctions","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2203.13125","title":"Intelligent Systematic Investment Agent: an ensemble of deep learning and evolutionary strategies","created":"2022-03-24","cited_by_count":0,"area":null},{"id":"2209.02160","title":"Improving Assistive Robotics with Deep Reinforcement Learning","created":"2022-09-05","cited_by_count":0,"area":null},{"id":"2301.08325","title":"Advanced Scaling Methods for VNF deployment with Reinforcement Learning","created":"2023-01-19","cited_by_count":0,"area":null},{"id":"2309.13181","title":"Diagnosing and exploiting the computational demands of videos games for deep reinforcement learning","created":"2023-09-22","cited_by_count":0,"area":null}],"next_cursor":"100"}