{"total":1081,"rows":[{"id":"2302.02948","title":"Efficient Online Reinforcement Learning with Offline Data","created":"2023-02-06","cited_by_count":363,"area":null},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288,"area":null},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247,"area":null},{"id":"2302.06692","title":"Guiding Pretraining in Reinforcement Learning with Large Language Models","created":"2023-02-13","cited_by_count":187,"area":null},{"id":"2102.11271","title":"Reinforcement Learning with Prototypical Representations","created":"2021-02-22","cited_by_count":179,"area":null},{"id":"2303.01486","title":"Understanding plasticity in neural networks","created":"2023-03-02","cited_by_count":174,"area":null},{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125,"area":null},{"id":"2212.01197","title":"FedALA: Adaptive Local Aggregation for Personalized Federated Learning","created":"2022-12-02","cited_by_count":122,"area":null},{"id":"2112.04553","title":"Recent Advances in Reinforcement Learning in Finance","created":"2021-12-08","cited_by_count":110,"area":null},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105,"area":null},{"id":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105,"area":null},{"id":"2110.10863","title":"Deep Generative Models in Engineering Design: A Review","created":"2021-10-21","cited_by_count":105,"area":null},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97,"area":null},{"id":"2108.11887","title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","created":"2021-08-26","cited_by_count":81,"area":null},{"id":"2402.02338","title":"NetLLM: Adapting Large Language Models for Networking","created":"2024-02-04","cited_by_count":78,"area":null},{"id":"2103.04000","title":"Off-Belief Learning","created":"2021-03-06","cited_by_count":75,"area":null},{"id":"2305.15555","title":"Deep Reinforcement Learning with Plasticity Injection","created":"2023-05-24","cited_by_count":74,"area":null},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"area":null},{"id":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73,"area":null},{"id":"2104.04132","title":"Replay in Deep Learning: Current Approaches and Missing Biological Elements","created":"2021-04-01","cited_by_count":72,"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":"2304.09870","title":"Heterogeneous-Agent Reinforcement Learning","created":"2023-04-19","cited_by_count":69,"area":null},{"id":"2106.06135","title":"DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning","created":"2021-06-11","cited_by_count":66,"area":null},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65,"area":null},{"id":"2206.01626","title":"Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress","created":"2022-06-03","cited_by_count":65,"area":null},{"id":"2307.03864","title":"When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment","created":"2023-07-07","cited_by_count":63,"area":null},{"id":"2311.10090","title":"JaxMARL: Multi-Agent RL Environments and Algorithms in JAX","created":"2023-11-16","cited_by_count":63,"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":"2208.07914","title":"PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm","created":"2022-08-16","cited_by_count":58,"area":null},{"id":"2204.00755","title":"Safe Reinforcement Learning via Shielding under Partial Observability","created":"2022-04-02","cited_by_count":56,"area":null},{"id":"2106.05087","title":"Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL","created":"2021-06-09","cited_by_count":55,"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":"2102.01168","title":"Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges","created":"2021-01-27","cited_by_count":50,"area":null},{"id":"2101.03958","title":"Evolving Reinforcement Learning Algorithms","created":"2021-01-08","cited_by_count":49,"area":null},{"id":"2106.04217","title":"Dynamic Sparse Training for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":49,"area":null},{"id":"2112.12288","title":"Safety and Liveness Guarantees through Reach-Avoid Reinforcement Learning","created":"2021-12-23","cited_by_count":49,"area":null},{"id":"2202.03825","title":"skrl: Modular and Flexible Library for Reinforcement Learning","created":"2022-02-08","cited_by_count":49,"area":null},{"id":"2104.14516","title":"Constructions in combinatorics via neural networks","created":"2021-04-29","cited_by_count":48,"area":null},{"id":"2107.02729","title":"AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning","created":"2021-07-06","cited_by_count":48,"area":null},{"id":"2306.01439","title":"Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction","created":"2023-06-02","cited_by_count":46,"area":null},{"id":"2106.04493","title":"A Deep Value-network Based Approach for Multi-Driver Order Dispatching","created":"2021-06-08","cited_by_count":45,"area":null},{"id":"2302.05209","title":"A Survey on Causal Reinforcement Learning","created":"2023-02-10","cited_by_count":45,"area":null},{"id":"2106.02940","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","created":"2021-06-05","cited_by_count":43,"area":null},{"id":"2107.12544","title":"Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning","created":"2021-07-27","cited_by_count":43,"area":null},{"id":"2210.05927","title":"Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning","created":"2022-10-12","cited_by_count":43,"area":null},{"id":"2106.09292","title":"CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing","created":"2021-06-17","cited_by_count":42,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"area":null},{"id":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","cited_by_count":42,"area":null},{"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":"2201.12096","title":"Mask-based Latent Reconstruction for Reinforcement Learning","created":"2022-01-28","cited_by_count":39,"area":null},{"id":"2202.07141","title":"Machine Learning in Aerodynamic Shape Optimization","created":"2022-02-15","cited_by_count":39,"area":null},{"id":"2205.13881","title":"Automated Dynamic Algorithm Configuration","created":"2022-05-27","cited_by_count":39,"area":null},{"id":"2304.05015","title":"Continual Semantic Segmentation with Automatic Memory Sample Selection","created":"2023-04-11","cited_by_count":39,"area":null},{"id":"2102.07920","title":"Training Larger Networks for Deep Reinforcement Learning","created":"2021-02-16","cited_by_count":38,"area":null},{"id":"2104.07886","title":"Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks","created":"2021-04-16","cited_by_count":38,"area":null},{"id":"2103.04529","title":"Self-Supervised Online Reward Shaping in Sparse-Reward Environments","created":"2021-03-08","cited_by_count":37,"area":null},{"id":"2204.11828","title":"Skill-based Meta-Reinforcement Learning","created":"2022-04-25","cited_by_count":37,"area":null},{"id":"2406.17630","title":"KANQAS: Kolmogorov-Arnold Network for Quantum Architecture Search","created":"2024-06-25","cited_by_count":37,"area":null},{"id":"2108.01316","title":"RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting","created":"2021-08-03","cited_by_count":36,"area":null},{"id":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36,"area":null},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2304.10466","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","created":"2023-04-20","cited_by_count":36,"area":null},{"id":"2310.08252","title":"MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning","created":"2023-10-12","cited_by_count":36,"area":null},{"id":"2106.06842","title":"Recomposing the Reinforcement Learning Building Blocks with Hypernetworks","created":"2021-06-12","cited_by_count":35,"area":null},{"id":"2205.14526","title":"Group-wise Reinforcement Feature Generation for Optimal and Explainable Representation Space Reconstruction","created":"2022-05-28","cited_by_count":35,"area":null},{"id":"2103.05115","title":"Deep reinforcement learning in medical imaging: A literature review","created":"2021-03-05","cited_by_count":34,"area":null},{"id":"2103.06426","title":"XDO: A Double Oracle Algorithm for Extensive-Form Games","created":"2021-03-11","cited_by_count":34,"area":null},{"id":"2107.09584","title":"Active 3D Shape Reconstruction from Vision and Touch","created":"2021-07-20","cited_by_count":34,"area":null},{"id":"2110.13484","title":"Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Survey","created":"2021-10-26","cited_by_count":34,"area":null},{"id":"2205.13536","title":"Verifying Learning-Based Robotic Navigation Systems","created":"2022-05-26","cited_by_count":33,"area":null},{"id":"2312.10256","title":"Multi-agent Reinforcement Learning: A Comprehensive Survey","created":"2023-12-15","cited_by_count":33,"area":null},{"id":"2104.08060","title":"MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks","created":"2021-04-16","cited_by_count":32,"area":null},{"id":"2207.07166","title":"K-level Reasoning for Zero-Shot Coordination in Hanabi","created":"2022-07-14","cited_by_count":32,"area":null},{"id":"2101.11992","title":"Acting in Delayed Environments with Non-Stationary Markov Policies","created":"2021-01-28","cited_by_count":31,"area":null},{"id":"2103.00445","title":"Ensemble Bootstrapping for Q-Learning","created":"2021-02-28","cited_by_count":31,"area":null},{"id":"2201.02373","title":"Mirror Learning: A Unifying Framework of Policy Optimisation","created":"2022-01-07","cited_by_count":31,"area":null},{"id":"2206.07922","title":"Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications","created":"2022-06-16","cited_by_count":30,"area":null},{"id":"2304.04150","title":"RoboPianist: Dexterous Piano Playing with Deep Reinforcement Learning","created":"2023-04-09","cited_by_count":30,"area":null},{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30,"area":null},{"id":"2301.11181","title":"Deep Laplacian-based Options for Temporally-Extended Exploration","created":"2023-01-26","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":"2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","created":"2023-05-29","cited_by_count":29,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2105.13623","title":"Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimation","created":"2021-05-28","cited_by_count":28,"area":null},{"id":"2110.04186","title":"Medical Dead-ends and Learning to Identify High-risk States and Treatments","created":"2021-10-08","cited_by_count":28,"area":null},{"id":"2206.00730","title":"The Phenomenon of Policy Churn","created":"2022-06-01","cited_by_count":28,"area":null},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2211.04324","title":"Machine Learning-Aided Operations and Communications of Unmanned Aerial Vehicles: A Contemporary Survey","created":"2022-11-07","cited_by_count":28,"area":null},{"id":"2106.02097","title":"A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning","created":"2021-06-03","cited_by_count":27,"area":null},{"id":"2202.08159","title":"Domain Adaptive Fake News Detection via Reinforcement Learning","created":"2022-02-16","cited_by_count":27,"area":null},{"id":"2304.02370","title":"Effective control of two-dimensional Rayleigh--B\\'enard convection: invariant multi-agent reinforcement learning is all you need","created":"2023-04-05","cited_by_count":27,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"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":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2212.13402","title":"Traceable Automatic Feature Transformation via Cascading Actor-Critic Agents","created":"2022-12-27","cited_by_count":26,"area":null},{"id":"2306.17833","title":"Resetting the Optimizer in Deep RL: An Empirical Study","created":"2023-06-30","cited_by_count":26,"area":null},{"id":"2106.05262","title":"TempoRL: Learning When to Act","created":"2021-06-09","cited_by_count":25,"area":null}],"next_cursor":"100"}