{"total":223,"rows":[{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196,"area":"deeprl"},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"id":"2402.02025","title":"A Survey of Constraint Formulations in Safe Reinforcement Learning","created":"2024-02-03","cited_by_count":44,"area":"deeprl"},{"id":"2402.17257","title":"RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences","created":"2024-02-27","cited_by_count":39,"area":"deeprl"},{"id":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38,"area":"deeprl"},{"id":"2602.02710","title":"Maximum Likelihood Reinforcement Learning","created":"2026-02-02","cited_by_count":36,"area":"deeprl"},{"id":"2404.14735","title":"Rank2Reward: Learning Shaped Reward Functions from Passive Video","created":"2024-04-23","cited_by_count":32,"area":"deeprl"},{"id":"2510.20817","title":"KL-Regularized Reinforcement Learning is Designed to Mode Collapse","created":"2025-10-23","cited_by_count":31,"area":"deeprl"},{"id":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"area":"deeprl"},{"id":"2404.03578","title":"Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithms","created":"2024-04-04","cited_by_count":26,"area":"deeprl"},{"id":"2408.01072","title":"A Survey on Self-play Methods in Reinforcement Learning","created":"2024-08-02","cited_by_count":26,"area":"deeprl"},{"id":"2404.08003","title":"Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis","created":"2024-04-09","cited_by_count":21,"area":"deeprl"},{"id":"2410.20254","title":"Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL","created":"2024-10-26","cited_by_count":21,"area":"deeprl"},{"id":"2406.03704","title":"Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking","created":"2024-06-06","cited_by_count":19,"area":"deeprl"},{"id":"2506.21872","title":"A Survey of Continual Reinforcement Learning","created":"2025-06-27","cited_by_count":18,"area":"deeprl"},{"id":"2407.03302","title":"A Review of the Applications of Deep Learning-Based Emergent Communication","created":"2024-07-03","cited_by_count":17,"area":"deeprl"},{"id":"2601.11087","title":"PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models","created":"2026-01-16","cited_by_count":17,"area":"deeprl"},{"id":"2403.06323","title":"A Reductions Approach to Risk-Sensitive Reinforcement Learning with Optimized Certainty Equivalents","created":"2024-03-10","cited_by_count":16,"area":"deeprl"},{"id":"2405.04657","title":"ACEGEN: Reinforcement learning of generative chemical agents for drug discovery","created":"2024-05-07","cited_by_count":14,"area":"deeprl"},{"id":"2407.07082","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","created":"2024-07-09","cited_by_count":14,"area":"deeprl"},{"id":"2508.10316","title":"Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances","created":"2025-08-14","cited_by_count":12,"area":"deeprl"},{"id":"2403.01410","title":"Barrier Functions Inspired Reward Shaping for Reinforcement Learning","created":"2024-03-03","cited_by_count":11,"area":"deeprl"},{"id":"2505.19281","title":"A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning","created":"2025-05-25","cited_by_count":11,"area":"deeprl"},{"id":"2405.07637","title":"Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback","created":"2024-05-13","cited_by_count":10,"area":"deeprl"},{"id":"2405.17061","title":"Provably Efficient Reinforcement Learning with Multinomial Logit Function Approximation","created":"2024-05-27","cited_by_count":10,"area":"deeprl"},{"id":"2601.12799","title":"FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions","created":"2026-01-19","cited_by_count":10,"area":"deeprl"},{"id":"2405.16390","title":"Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning","created":"2024-05-26","cited_by_count":9,"area":"deeprl"},{"id":"2408.03195","title":"RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning","created":"2024-08-06","cited_by_count":9,"area":"deeprl"},{"id":"2411.05234","title":"Performative Reinforcement Learning with Linear Markov Decision Process","created":"2024-11-07","cited_by_count":9,"area":"deeprl"},{"id":"2508.08189","title":"Reinforcement Learning for Large Model: A Survey","created":"2025-08-11","cited_by_count":9,"area":"deeprl"},{"id":"2409.12799","title":"The Central Role of the Loss Function in Reinforcement Learning","created":"2024-09-19","cited_by_count":8,"area":"deeprl"},{"id":"2410.21795","title":"Robot Policy Learning with Temporal Optimal Transport Reward","created":"2024-10-29","cited_by_count":8,"area":"deeprl"},{"id":"2509.18648","title":"SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer","created":"2025-09-23","cited_by_count":8,"area":"deeprl"},{"id":"2405.15541","title":"Learning Generalizable Human Motion Generator with Reinforcement Learning","created":"2024-05-24","cited_by_count":7,"area":"deeprl"},{"id":"2406.03102","title":"DEER: A Delay-Resilient Framework for Reinforcement Learning with Variable Delays","created":"2024-06-05","cited_by_count":7,"area":"deeprl"},{"id":"2407.07364","title":"Real-time system optimal traffic routing under uncertainties -- Can physics models boost reinforcement learning?","created":"2024-07-10","cited_by_count":7,"area":"deeprl"},{"id":"2501.13448","title":"BMG-Q: Localized Bipartite Match Graph Attention Q-Learning for Ride-Pooling Order Dispatch","created":"2025-01-23","cited_by_count":7,"area":"deeprl"},{"id":"2505.20268","title":"Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits","created":"2025-05-26","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":"2509.25424","title":"Polychromic Objectives for Reinforcement Learning","created":"2025-09-29","cited_by_count":7,"area":"deeprl"},{"id":"2511.20066","title":"SOMBRL: Scalable and Optimistic Model-Based RL","created":"2025-11-25","cited_by_count":7,"area":"deeprl"},{"id":"2403.14156","title":"Policy Mirror Descent with Lookahead","created":"2024-03-21","cited_by_count":6,"area":"deeprl"},{"id":"2404.15199","title":"Reinforcement Learning with Adaptive Regularization for Safe Control of Critical Systems","created":"2024-04-23","cited_by_count":6,"area":"deeprl"},{"id":"2405.12535","title":"PhiBE: A PDE-based Bellman Equation for Continuous Time Policy Evaluation","created":"2024-05-21","cited_by_count":6,"area":"deeprl"},{"id":"2407.04803","title":"The Impact of Quantization and Pruning on Deep Reinforcement Learning Models","created":"2024-07-05","cited_by_count":6,"area":"deeprl"},{"id":"2505.24161","title":"Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control","created":"2025-05-30","cited_by_count":6,"area":"deeprl"},{"id":"2506.07459","title":"ProteinZero: Self-Improving Protein Generation via Online Reinforcement Learning","created":"2025-06-09","cited_by_count":6,"area":"deeprl"},{"id":"2508.03768","title":"ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning","created":"2025-08-05","cited_by_count":6,"area":"deeprl"},{"id":"2601.19612","title":"Safe Exploration via Policy Priors","created":"2026-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2606.30376","title":"FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification","created":"2026-06-29","cited_by_count":6,"area":"deeprl"},{"id":"2407.03065","title":"Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes","created":"2024-07-03","cited_by_count":5,"area":"deeprl"},{"id":"2408.00751","title":"A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence","created":"2024-08-01","cited_by_count":5,"area":"deeprl"},{"id":"2408.05885","title":"GFlowNet Training by Policy Gradients","created":"2024-08-12","cited_by_count":5,"area":"deeprl"},{"id":"2409.19437","title":"Strongly-polynomial time and validation analysis of policy gradient methods","created":"2024-09-28","cited_by_count":5,"area":"deeprl"},{"id":"2503.08934","title":"Near-Optimal Sample Complexity for Iterated CVaR Reinforcement Learning with a Generative Model","created":"2025-03-11","cited_by_count":5,"area":"deeprl"},{"id":"2505.10802","title":"Attention-Based Reward Shaping for Sparse and Delayed Rewards","created":"2025-05-16","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":"2601.21669","title":"Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling","created":"2026-01-29","cited_by_count":5,"area":"deeprl"},{"id":"2602.01156","title":"PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learning","created":"2026-02-01","cited_by_count":5,"area":"deeprl"},{"id":"2602.08934","title":"StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors","created":"2026-02-09","cited_by_count":5,"area":"deeprl"},{"id":"2401.13020","title":"A Safe Reinforcement Learning Algorithm for Supervisory Control of Power Plants","created":"2024-01-23","cited_by_count":4,"area":"deeprl"},{"id":"2407.12185","title":"Satisficing Exploration for Deep Reinforcement Learning","created":"2024-07-16","cited_by_count":4,"area":"deeprl"},{"id":"2407.16807","title":"In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning","created":"2024-07-23","cited_by_count":4,"area":"deeprl"},{"id":"2503.19037","title":"Evolutionary Policy Optimization","created":"2025-03-24","cited_by_count":4,"area":"deeprl"},{"id":"2506.03066","title":"Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function","created":"2025-06-03","cited_by_count":4,"area":"deeprl"},{"id":"2506.03757","title":"PPO in the Fisher-Rao geometry","created":"2025-06-04","cited_by_count":4,"area":"deeprl"},{"id":"2508.17850","title":"GEPO: Group Expectation Policy Optimization for Stable Heterogeneous Reinforcement Learning","created":"2025-08-25","cited_by_count":4,"area":"deeprl"},{"id":"2510.02490","title":"Improved Robustness of Deep Reinforcement Learning for Control of Time-Varying Systems by Bounded Extremum Seeking","created":"2025-10-02","cited_by_count":4,"area":"deeprl"},{"id":"2510.16132","title":"A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies","created":"2025-10-17","cited_by_count":4,"area":"deeprl"},{"id":"2510.20725","title":"No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes","created":"2025-10-23","cited_by_count":4,"area":"deeprl"},{"id":"2602.01460","title":"Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator","created":"2026-02-01","cited_by_count":4,"area":"deeprl"},{"id":"2409.14557","title":"Exploiting Exogenous Structure for Sample-Efficient Reinforcement Learning","created":"2024-09-22","cited_by_count":3,"area":"deeprl"},{"id":"2412.11138","title":"Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation","created":"2024-12-15","cited_by_count":3,"area":"deeprl"},{"id":"2505.11661","title":"Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning","created":"2025-05-16","cited_by_count":3,"area":"deeprl"},{"id":"2506.00388","title":"CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries","created":"2025-05-31","cited_by_count":3,"area":"deeprl"},{"id":"2506.00700","title":"Central Path Proximal Policy Optimization","created":"2025-05-31","cited_by_count":3,"area":"deeprl"},{"id":"2506.09562","title":"TooBadRL: Trigger Optimization to Boost Effectiveness of Backdoor Attacks on Deep Reinforcement Learning","created":"2025-06-11","cited_by_count":3,"area":"deeprl"},{"id":"2511.06812","title":"Convergence of Actor-Critic Learning for Mean Field Games and Mean Field Control in Continuous Spaces","created":"2025-11-10","cited_by_count":3,"area":"deeprl"},{"id":"2512.06244","title":"Auto-exploration for online reinforcement learning","created":"2025-12-06","cited_by_count":3,"area":"deeprl"},{"id":"2512.14202","title":"Understanding and Improving Hyperbolic Deep Reinforcement Learning","created":"2025-12-16","cited_by_count":3,"area":"deeprl"},{"id":"2512.15036","title":"Spectral Representation-based Reinforcement Learning","created":"2025-12-17","cited_by_count":3,"area":"deeprl"},{"id":"2512.19366","title":"Learning General Policies with Policy Gradient Methods","created":"2025-12-22","cited_by_count":3,"area":"deeprl"},{"id":"2601.04698","title":"TourPlanner: A Competitive Consensus Framework with Constraint-Gated Reinforcement Learning for Travel Planning","created":"2026-01-08","cited_by_count":3,"area":"deeprl"},{"id":"2602.11399","title":"Can We Really Learn One Representation to Optimize All Rewards?","created":"2026-02-11","cited_by_count":3,"area":"deeprl"},{"id":"2603.14608","title":"Delightful Policy Gradient","created":"2026-03-15","cited_by_count":3,"area":"deeprl"},{"id":"2605.15971","title":"OHP-RL: Online Human Preference as Guidance in Reinforcement Learning for Robot Manipulation","created":"2026-05-15","cited_by_count":3,"area":"deeprl"},{"id":"2606.06053","title":"Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification","created":"2026-06-04","cited_by_count":3,"area":"deeprl"},{"id":"2607.08444","title":"Statistical Efficiency and Inference of Quantile Distributional Reinforcement Learning","created":"2026-07-09","cited_by_count":3,"area":"deeprl"},{"id":"2404.05950","title":"Efficient Multi-Task Reinforcement Learning via Task-Specific Action Correction","created":"2024-04-09","cited_by_count":2,"area":"deeprl"},{"id":"2405.01760","title":"Reinforcement Learning-Guided Semi-Supervised Learning","created":"2024-05-02","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":"2406.03862","title":"Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation","created":"2024-06-06","cited_by_count":2,"area":"deeprl"},{"id":"2406.07897","title":"When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions","created":"2024-06-12","cited_by_count":2,"area":"deeprl"},{"id":"2406.17902","title":"Domain Adaptation of Echocardiography Segmentation Via Reinforcement Learning","created":"2024-06-25","cited_by_count":2,"area":"deeprl"},{"id":"2410.06213","title":"RL, but don't do anything I wouldn't do","created":"2024-10-08","cited_by_count":2,"area":"deeprl"},{"id":"2501.07508","title":"Improving DeFi Accessibility through Efficient Liquidity Provisioning with Deep Reinforcement Learning","created":"2025-01-13","cited_by_count":2,"area":"deeprl"},{"id":"2502.16195","title":"Statistical Inference in Reinforcement Learning: A Selective Survey","created":"2025-02-22","cited_by_count":2,"area":"deeprl"},{"id":"2505.21236","title":"Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies","created":"2025-05-27","cited_by_count":2,"area":"deeprl"},{"id":"2505.21852","title":"A Provable Approach for End-to-End Safe Reinforcement Learning","created":"2025-05-28","cited_by_count":2,"area":"deeprl"},{"id":"2507.14444","title":"Statistical and Algorithmic Foundations of Reinforcement Learning","created":"2025-07-19","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}