{"total":143,"rows":[{"id":"2506.01939","title":"Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning","created":"2025-06-02","cited_by_count":559,"area":"lr"},{"id":"2302.04659","title":"ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills","created":"2023-02-09","cited_by_count":327,"area":null},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186,"area":null},{"id":"2209.14548","title":"Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling","created":"2022-09-29","cited_by_count":182,"area":"offlinerl"},{"id":"2208.06677","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","created":"2022-08-13","cited_by_count":174,"area":null},{"id":"2110.05038","title":"Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs","created":"2021-10-11","cited_by_count":122,"area":null},{"id":"2210.07105","title":"CORL: Research-oriented Deep Offline Reinforcement Learning Library","created":"2022-10-13","cited_by_count":119,"area":"offlinerl"},{"id":"2111.03788","title":"d3rlpy: An Offline Deep Reinforcement Learning Library","created":"2021-11-06","cited_by_count":84,"area":"offlinerl"},{"id":"2305.09304","title":"OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Research","created":"2023-05-16","cited_by_count":80,"area":null},{"id":"2306.17100","title":"RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","created":"2023-06-29","cited_by_count":71,"area":null},{"id":"2206.10558","title":"EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Engine","created":"2022-06-21","cited_by_count":62,"area":null},{"id":"2306.00577","title":"TorchRL: A data-driven decision-making library for PyTorch","created":"2023-06-01","cited_by_count":60,"area":null},{"id":"2306.09303","title":"Datasets and Benchmarks for Offline Safe Reinforcement Learning","created":"2023-06-15","cited_by_count":59,"area":"offlinerl"},{"id":"2303.17503","title":"Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning","created":"2023-03-29","cited_by_count":51,"area":null},{"id":"2407.17032","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","created":"2024-07-24","cited_by_count":46,"area":"deeprl"},{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37,"area":null},{"id":"2210.06835","title":"Multi-agent Dynamic Algorithm Configuration","created":"2022-10-13","cited_by_count":36,"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":"2407.01704","title":"Weight Clipping for Deep Continual and Reinforcement Learning","created":"2024-07-01","cited_by_count":29,"area":"deeprl"},{"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":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2403.09110","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","created":"2024-03-14","cited_by_count":26,"area":"deeprl"},{"id":"2201.07211","title":"Human-Level Control through Directly-Trained Deep Spiking Q-Networks","created":"2021-12-13","cited_by_count":25,"area":null},{"id":"2307.07907","title":"Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation","created":"2023-07-15","cited_by_count":25,"area":null},{"id":"2406.12905","title":"PufferLib: Making Reinforcement Learning Libraries and Environments Play Nice","created":"2024-06-11","cited_by_count":24,"area":null},{"id":"2110.12628","title":"Recurrent Off-policy Baselines for Memory-based Continuous Control","created":"2021-10-25","cited_by_count":21,"area":null},{"id":"2210.13708","title":"MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library","created":"2022-10-11","cited_by_count":21,"area":null},{"id":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17,"area":"deeprl"},{"id":"2309.00711","title":"Learning Shared Safety Constraints from Multi-task Demonstrations","created":"2023-09-01","cited_by_count":15,"area":null},{"id":"2305.13681","title":"GUARD: A Safe Reinforcement Learning Benchmark","created":"2023-05-23","cited_by_count":13,"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":"2203.04735","title":"A Survey on Reinforcement Learning Methods in Character Animation","created":"2022-03-07","cited_by_count":12,"area":null},{"id":"2208.01682","title":"Heterogeneous-Agent Mirror Learning: A Continuum of Solutions to Cooperative MARL","created":"2022-08-02","cited_by_count":12,"area":null},{"id":"2406.12241","title":"More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling","created":"2024-06-18","cited_by_count":12,"area":"deeprl"},{"id":"2210.04365","title":"ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward","created":"2022-10-09","cited_by_count":11,"area":null},{"id":"2401.12497","title":"Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning","created":"2024-01-23","cited_by_count":11,"area":"deeprl"},{"id":"2501.15893","title":"Benchmarking Quantum Reinforcement Learning","created":"2025-01-27","cited_by_count":10,"area":"deeprl"},{"id":"2205.10868","title":"Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation","created":"2022-05-22","cited_by_count":9,"area":null},{"id":"2308.07795","title":"Learning to Identify Critical States for Reinforcement Learning from Videos","created":"2023-08-15","cited_by_count":9,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2402.15164","title":"EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender Systems","created":"2024-02-23","cited_by_count":9,"area":"deeprl"},{"id":"2410.18416","title":"SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions","created":"2024-10-24","cited_by_count":9,"area":null},{"id":"2505.17745","title":"MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization","created":"2025-05-23","cited_by_count":9,"area":null},{"id":"2206.09203","title":"Interactive Visual Reasoning under Uncertainty","created":"2022-06-18","cited_by_count":8,"area":"lr"},{"id":"2310.09426","title":"Offline Reinforcement Learning for Optimizing Production Bidding Policies","created":"2023-10-13","cited_by_count":8,"area":"offlinerl"},{"id":"2405.18610","title":"DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment Regime","created":"2024-05-28","cited_by_count":8,"area":"deeprl"},{"id":"2411.05614","title":"Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey","created":"2024-11-08","cited_by_count":8,"area":"deeprl"},{"id":"2411.19671","title":"On the Performance Analysis of Momentum Method: A Frequency Domain Perspective","created":"2024-11-29","cited_by_count":8,"area":null},{"id":"2210.12262","title":"Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2301.11490","title":"Neural Episodic Control with State Abstraction","created":"2023-01-27","cited_by_count":7,"area":null},{"id":"2306.07553","title":"DenseLight: Efficient Control for Large-scale Traffic Signals with Dense Feedback","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2307.01995","title":"Dynamic Feature-based Deep Reinforcement Learning for Flow Control of Circular Cylinder with Sparse Surface Pressure Sensing","created":"2023-07-05","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":"2310.19927","title":"Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms","created":"2023-10-30","cited_by_count":7,"area":null},{"id":"2405.03064","title":"RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation","created":"2024-05-05","cited_by_count":7,"area":"deeprl"},{"id":"2505.10482","title":"Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps","created":"2025-05-15","cited_by_count":7,"area":"diffusion"},{"id":"2210.07802","title":"Object-Category Aware Reinforcement Learning","created":"2022-10-13","cited_by_count":6,"area":null},{"id":"2311.18736","title":"Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms","created":"2023-11-30","cited_by_count":6,"area":null},{"id":"2403.09940","title":"Global Convergence Guarantees for Federated Policy Gradient Methods with Adversaries","created":"2024-03-15","cited_by_count":6,"area":"deeprl"},{"id":"2405.15831","title":"Transmission Interface Power Flow Adjustment: A Deep Reinforcement Learning Approach based on Multi-task Attribution Map","created":"2024-05-24","cited_by_count":6,"area":"deeprl"},{"id":"2410.01101","title":"Exploiting Structure in Offline Multi-Agent RL: The Benefits of Low Interaction Rank","created":"2024-10-01","cited_by_count":6,"area":"offlinerl"},{"id":"2412.00744","title":"Open-World Drone Active Tracking with Goal-Centered Rewards","created":"2024-12-01","cited_by_count":6,"area":"deeprl"},{"id":"2310.05205","title":"GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning Models","created":"2023-10-08","cited_by_count":5,"area":null},{"id":"2312.16248","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2505.19247","title":"Improving Value Estimation Critically Enhances Vanilla Policy Gradient","created":"2025-05-25","cited_by_count":5,"area":"deeprl"},{"id":"2112.07535","title":"Scientific Discovery and the Cost of Measurement -- Balancing Information and Cost in Reinforcement Learning","created":"2021-12-14","cited_by_count":4,"area":null},{"id":"2212.00253","title":"Distributed Deep Reinforcement Learning: A Survey and A Multi-Player Multi-Agent Learning Toolbox","created":"2022-12-01","cited_by_count":4,"area":null},{"id":"2303.13117","title":"RLOR: A Flexible Framework of Deep Reinforcement Learning for Operation Research","created":"2023-03-23","cited_by_count":4,"area":null},{"id":"2306.03530","title":"RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control","created":"2023-06-06","cited_by_count":4,"area":null},{"id":"2306.07307","title":"Online Prototype Alignment for Few-shot Policy Transfer","created":"2023-06-12","cited_by_count":4,"area":null},{"id":"2401.03546","title":"NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds","created":"2024-01-07","cited_by_count":4,"area":null},{"id":"2409.05344","title":"GOPT: Generalizable Online 3D Bin Packing via Transformer-based Deep Reinforcement Learning","created":"2024-09-09","cited_by_count":4,"area":"deeprl"},{"id":"2507.11060","title":"Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing","created":"2025-07-15","cited_by_count":4,"area":"deeprl"},{"id":"2309.16382","title":"RLLTE: Long-Term Evolution Project of Reinforcement Learning","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2501.00913","title":"$\\beta$-DQN: Improving Deep Q-Learning By Evolving the Behavior","created":"2025-01-01","cited_by_count":3,"area":"deeprl"},{"id":"2501.15618","title":"Your Learned Constraint is Secretly a Backward Reachable Tube","created":"2025-01-26","cited_by_count":3,"area":null},{"id":"2504.04911","title":"IterMask3D: Unsupervised Anomaly Detection and Segmentation with Test-Time Iterative Mask Refinement in 3D Brain MR","created":"2025-04-07","cited_by_count":3,"area":null},{"id":"2510.27153","title":"Exploring Landscapes for Better Minima along Valleys","created":"2025-10-31","cited_by_count":3,"area":null},{"id":"2603.06413","title":"A Reference Architecture of Reinforcement Learning Frameworks","created":"2026-03-06","cited_by_count":3,"area":"deeprl"},{"id":"2603.23838","title":"Learning-guided Prioritized Planning for Lifelong Multi-Agent Path Finding in Warehouse Automation","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2109.09470","title":"ACReL: Adversarial Conditional value-at-risk Reinforcement Learning","created":"2021-09-20","cited_by_count":2,"area":null},{"id":"2207.11432","title":"Driver Dojo: A Benchmark for Generalizable Reinforcement Learning for Autonomous Driving","created":"2022-07-23","cited_by_count":2,"area":"driving"},{"id":"2209.07074","title":"On the Reuse Bias in Off-Policy Reinforcement Learning","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2304.09869","title":"Evolving Constrained Reinforcement Learning Policy","created":"2023-04-19","cited_by_count":2,"area":null},{"id":"2312.03290","title":"Can language agents be alternatives to PPO? A Preliminary Empirical Study On OpenAI Gym","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2402.00972","title":"Closure Discovery for Coarse-Grained Partial Differential Equations Using Grid-based Reinforcement Learning","created":"2024-02-01","cited_by_count":2,"area":"deeprl"},{"id":"2405.04549","title":"ClothPPO: A Proximal Policy Optimization Enhancing Framework for Robotic Cloth Manipulation with Observation-Aligned Action Spaces","created":"2024-05-05","cited_by_count":2,"area":"deeprl"},{"id":"2406.04920","title":"Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning","created":"2024-06-07","cited_by_count":2,"area":"deeprl"},{"id":"2412.09466","title":"Distributional Reinforcement Learning based Integrated Decision Making and Control for Autonomous Surface Vehicles","created":"2024-12-12","cited_by_count":2,"area":"deeprl"},{"id":"2501.19128","title":"Shaping Sparse Rewards in Reinforcement Learning: A Semi-supervised Approach","created":"2025-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2502.10784","title":"Preconditioned Inexact Stochastic ADMM for Deep Model","created":"2025-02-15","cited_by_count":2,"area":null},{"id":"2502.15345","title":"Efficiently Solving Discounted MDPs with Predictions on Transition Matrices","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2504.14422","title":"Optimal Lattice Boltzmann Closures through Multi-Agent Reinforcement Learning","created":"2025-04-19","cited_by_count":2,"area":null},{"id":"2204.07543","title":"CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection","created":"2022-04-15","cited_by_count":1,"area":null},{"id":"2209.10072","title":"On the Convergence Theory of Meta Reinforcement Learning with Personalized Policies","created":"2022-09-21","cited_by_count":1,"area":null},{"id":"2211.15205","title":"CIM: Constrained Intrinsic Motivation for Sparse-Reward Continuous Control","created":"2022-11-28","cited_by_count":1,"area":null},{"id":"2212.02620","title":"Benchmarking Offline Reinforcement Learning Algorithms for E-Commerce Order Fraud Evaluation","created":"2022-12-05","cited_by_count":1,"area":"offlinerl"},{"id":"2305.13824","title":"Constrained Reinforcement Learning for Dynamic Material Handling","created":"2023-05-23","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":"2403.10487","title":"Stimulate the Potential of Robots via Competition","created":"2024-03-15","cited_by_count":1,"area":null}],"next_cursor":"100"}