{"total":69,"rows":[{"id":"2408.03539","title":"Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes","created":"2024-08-07","cited_by_count":176,"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":"2502.13187","title":"A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Models","created":"2025-02-18","cited_by_count":38,"area":"deeprl"},{"id":"2402.06819","title":"Monitored Markov Decision Processes","created":"2024-02-09","cited_by_count":10,"area":"deeprl"},{"id":"2409.07569","title":"A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges","created":"2024-09-11","cited_by_count":10,"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":"2505.19785","title":"medDreamer: Model-Based Reinforcement Learning with Latent Imagination on Complex EHRs for Clinical Decision Support","created":"2025-05-26","cited_by_count":9,"area":"deeprl"},{"id":"2405.01327","title":"Constrained Reinforcement Learning Under Model Mismatch","created":"2024-05-02","cited_by_count":8,"area":"deeprl"},{"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":"2408.11943","title":"Advances in Preference-based Reinforcement Learning: A Review","created":"2024-08-21","cited_by_count":8,"area":"deeprl"},{"id":"2502.16816","title":"Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning","created":"2025-02-24","cited_by_count":7,"area":"deeprl"},{"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":"2404.03774","title":"Exploration is Harder than Prediction: Cryptographically Separating Reinforcement Learning from Supervised Learning","created":"2024-04-04","cited_by_count":6,"area":"deeprl"},{"id":"2406.05646","title":"ICU-Sepsis: A Benchmark MDP Built from Real Medical Data","created":"2024-06-09","cited_by_count":6,"area":"deeprl"},{"id":"2406.13909","title":"Beyond Optimism: Exploration With Partially Observable Rewards","created":"2024-06-20","cited_by_count":6,"area":"deeprl"},{"id":"2402.02165","title":"Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error","created":"2024-02-03","cited_by_count":4,"area":"deeprl"},{"id":"2402.15957","title":"DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning","created":"2024-02-25","cited_by_count":4,"area":"deeprl"},{"id":"2406.11640","title":"Linear Bellman Completeness Suffices for Efficient Online Reinforcement Learning with Few Actions","created":"2024-06-17","cited_by_count":4,"area":"deeprl"},{"id":"2501.10605","title":"Wasserstein Adaptive Value Estimation for Actor-Critic Reinforcement Learning","created":"2025-01-17","cited_by_count":4,"area":"deeprl"},{"id":"2401.05233","title":"Taming \"data-hungry\" reinforcement learning? Stability in continuous state-action spaces","created":"2024-01-10","cited_by_count":3,"area":"deeprl"},{"id":"2401.12849","title":"Learning safety critics via a non-contractive binary bellman operator","created":"2024-01-23","cited_by_count":3,"area":"deeprl"},{"id":"2402.07107","title":"Echoes of Socratic Doubt: Embracing Uncertainty in Calibrated Evidential Reinforcement Learning","created":"2024-02-11","cited_by_count":3,"area":"deeprl"},{"id":"2407.00364","title":"Medical Knowledge Integration into Reinforcement Learning Algorithms for Dynamic Treatment Regimes","created":"2024-06-29","cited_by_count":3,"area":"deeprl"},{"id":"2407.20917","title":"How to Choose a Reinforcement-Learning Algorithm","created":"2024-07-30","cited_by_count":3,"area":"deeprl"},{"id":"2508.21101","title":"Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI","created":"2025-08-28","cited_by_count":3,"area":"deeprl"},{"id":"2510.24482","title":"Sample-efficient and Scalable Exploration in Continuous-Time RL","created":"2025-10-28","cited_by_count":3,"area":"deeprl"},{"id":"2602.14505","title":"Formally Verifying and Explaining Sepsis Treatment Policies with COOL-MC","created":"2026-02-16","cited_by_count":3,"area":"deeprl"},{"id":"2405.03967","title":"SwiftRL: Towards Efficient Reinforcement Learning on Real Processing-In-Memory Systems","created":"2024-05-07","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":"2408.00147","title":"Formal Ethical Obligations in Reinforcement Learning Agents: Verification and Policy Updates","created":"2024-07-31","cited_by_count":2,"area":"deeprl"},{"id":"2412.11743","title":"Generalized Bayesian deep reinforcement learning","created":"2024-12-16","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":"2404.03105","title":"Methodology for Interpretable Reinforcement Learning for Optimizing Mechanical Ventilation","created":"2024-04-03","cited_by_count":1,"area":"deeprl"},{"id":"2404.17187","title":"An Explainable Deep Reinforcement Learning Model for Warfarin Maintenance Dosing Using Policy Distillation and Action Forging","created":"2024-04-26","cited_by_count":1,"area":"deeprl"},{"id":"2411.00336","title":"StepCountJITAI: simulation environment for RL with application to physical activity adaptive intervention","created":"2024-11-01","cited_by_count":1,"area":"deeprl"},{"id":"2411.13116","title":"Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning","created":"2024-11-20","cited_by_count":1,"area":"deeprl"},{"id":"2505.12701","title":"Counterfactual Explanations for Continuous Action Reinforcement Learning","created":"2025-05-19","cited_by_count":1,"area":"deeprl"},{"id":"2506.01167","title":"Accelerated Learning with Linear Temporal Logic using Differentiable Simulation","created":"2025-06-01","cited_by_count":1,"area":"deeprl"},{"id":"2507.08848","title":"Assuring the Safety of Reinforcement Learning Components: AMLAS-RL","created":"2025-07-08","cited_by_count":1,"area":"deeprl"},{"id":"2602.16274","title":"Regret and Sample Complexity of Online Q-Learning via Concentration of Stochastic Approximation with Time-Inhomogeneous Markov Chains","created":"2026-02-18","cited_by_count":1,"area":"deeprl"},{"id":"2607.13175","title":"SteinGate: Tail-Sensitive Safe Reinforcement Learning via Stein Discrepancy","created":"2026-07-14","cited_by_count":1,"area":"deeprl"},{"id":"2401.10794","title":"Deep Reinforcement Learning Empowered Activity-Aware Dynamic Health Monitoring Systems","created":"2024-01-19","cited_by_count":0,"area":"deeprl"},{"id":"2402.03771","title":"Reinforcement Learning from Bagged Reward","created":"2024-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2403.10761","title":"Scheduling Drone and Mobile Charger via Hybrid-Action Deep Reinforcement Learning","created":"2024-03-16","cited_by_count":0,"area":"deeprl"},{"id":"2409.16791","title":"Symbolic State Partitioning for Reinforcement Learning","created":"2024-09-25","cited_by_count":0,"area":"deeprl"},{"id":"2411.11457","title":"Upside-Down Reinforcement Learning for More Interpretable Optimal Control","created":"2024-11-18","cited_by_count":0,"area":"deeprl"},{"id":"2412.05906","title":"Reinforcement Learning for a Discrete-Time Linear-Quadratic Control Problem with an Application","created":"2024-12-08","cited_by_count":0,"area":"deeprl"},{"id":"2412.17908","title":"Trading Devil RL: Backdoor attack via Stock market, Bayesian Optimization and Reinforcement Learning","created":"2024-12-23","cited_by_count":0,"area":"deeprl"},{"id":"2503.08867","title":"Zero-Shot Action Generalization with Limited Observations","created":"2025-03-11","cited_by_count":0,"area":"deeprl"},{"id":"2504.03040","title":"Safety Modulation: Enhancing Safety in Reinforcement Learning through Cost-Modulated Rewards","created":"2025-04-03","cited_by_count":0,"area":"deeprl"},{"id":"2504.12557","title":"TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels","created":"2025-04-17","cited_by_count":0,"area":"deeprl"},{"id":"2504.16635","title":"Bridging Econometrics and AI: VaR Estimation via Reinforcement Learning and GARCH Models","created":"2025-04-23","cited_by_count":0,"area":"deeprl"},{"id":"2507.04187","title":"Where to Intervene: Action Selection in Deep Reinforcement Learning","created":"2025-07-05","cited_by_count":0,"area":"deeprl"},{"id":"2509.09208","title":"Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning","created":"2025-09-11","cited_by_count":0,"area":"deeprl"},{"id":"2510.22017","title":"Do You Trust the Process?: Modeling Institutional Trust for Community Adoption of Reinforcement Learning Policies","created":"2025-10-24","cited_by_count":0,"area":"deeprl"},{"id":"2511.02577","title":"Directional-Clamp PPO","created":"2025-11-04","cited_by_count":0,"area":"deeprl"},{"id":"2512.10492","title":"UACER: An Uncertainty-Adaptive Critic Ensemble Framework for Robust Adversarial Reinforcement Learning","created":"2025-12-11","cited_by_count":0,"area":"deeprl"},{"id":"2602.05379","title":"Variance Reduction Based Experience Replay for Policy Optimization","created":"2026-02-05","cited_by_count":0,"area":"deeprl"},{"id":"2602.14559","title":"Fluid-Agent Reinforcement Learning","created":"2026-02-16","cited_by_count":0,"area":"deeprl"},{"id":"2603.25771","title":"Empowering Epidemic Response: The Role of Reinforcement Learning in Infectious Disease Control","created":"2026-03-26","cited_by_count":0,"area":"deeprl"},{"id":"2604.04334","title":"Boosted Distributional Reinforcement Learning: Analysis and Healthcare Applications","created":"2026-04-06","cited_by_count":0,"area":"deeprl"},{"id":"2604.10062","title":"When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs","created":"2026-04-11","cited_by_count":0,"area":"deeprl"},{"id":"2604.15201","title":"RL-STPA: Adapting System-Theoretic Hazard Analysis for Safety-Critical Reinforcement Learning","created":"2026-04-16","cited_by_count":0,"area":"deeprl"},{"id":"2606.01028","title":"A Unified Benchmark for Dynamic Medical Treatment Reinforcement Learning","created":"2026-05-31","cited_by_count":0,"area":"deeprl"},{"id":"2606.06800","title":"Exploring Reinforcement Learning for Fluid Transitions Between Clinical Mental Healthcare and Everyday Wellness Support","created":"2026-06-05","cited_by_count":0,"area":"deeprl"},{"id":"2607.16999","title":"Counterfactual Shapley Credit Assignment","created":"2026-07-18","cited_by_count":0,"area":"deeprl"},{"id":"2609.12264","title":"Adaptive Chemotherapy Control under Tumor Heterogeneity via Reinforcement Learning","created":"2026-09-10","cited_by_count":0,"area":"deeprl"},{"id":"2609.23374","title":"The Evidence Ladder for Reinforcement Learning in Healthcare: From Retrospective Policies to Trusted Interventions","created":"2026-09-20","cited_by_count":0,"area":"deeprl"},{"id":"2609.24750","title":"Reinforcement Learning in Operational Research: A Technical Review and Practical Roadmap","created":"2026-09-21","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}