{"total":176,"rows":[{"id":"2407.04811","title":"Simplifying Deep Temporal Difference Learning","created":"2024-07-05","cited_by_count":78,"area":"deeprl"},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"id":"2402.12479","title":"In value-based deep reinforcement learning, a pruned network is a good network","created":"2024-02-19","cited_by_count":39,"area":"deeprl"},{"id":"2403.09110","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","created":"2024-03-14","cited_by_count":26,"area":"deeprl"},{"id":"2406.17523","title":"On the consistency of hyper-parameter selection in value-based deep reinforcement learning","created":"2024-06-25","cited_by_count":21,"area":"deeprl"},{"id":"2506.21872","title":"A Survey of Continual Reinforcement Learning","created":"2025-06-27","cited_by_count":18,"area":"deeprl"},{"id":"2407.07787","title":"Continuous Control with Coarse-to-fine Reinforcement Learning","created":"2024-07-10","cited_by_count":17,"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":"2403.02290","title":"Koopman-Assisted Reinforcement Learning","created":"2024-03-04","cited_by_count":11,"area":"deeprl"},{"id":"2507.23172","title":"Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks","created":"2025-07-31","cited_by_count":11,"area":"deeprl"},{"id":"2411.12155","title":"Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning","created":"2024-11-19","cited_by_count":10,"area":"deeprl"},{"id":"2404.14238","title":"Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research Trajectories","created":"2024-04-22","cited_by_count":9,"area":"deeprl"},{"id":"2401.02349","title":"A Survey Analyzing Generalization in Deep Reinforcement Learning","created":"2024-01-04","cited_by_count":8,"area":"deeprl"},{"id":"2402.12874","title":"Skill or Luck? Return Decomposition via Advantage Functions","created":"2024-02-20","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":"2407.14151","title":"A Comparative Study of Deep Reinforcement Learning Models: DQN vs PPO vs A2C","created":"2024-07-19","cited_by_count":8,"area":"deeprl"},{"id":"2403.15267","title":"Parametric PDE Control with Deep Reinforcement Learning and Differentiable L0-Sparse Polynomial Policies","created":"2024-03-22","cited_by_count":7,"area":"deeprl"},{"id":"2406.14537","title":"MacroHFT: Memory Augmented Context-aware Reinforcement Learning On High Frequency Trading","created":"2024-06-20","cited_by_count":7,"area":"deeprl"},{"id":"2407.04522","title":"Graph Reinforcement Learning for Power Grids: A Comprehensive Survey","created":"2024-07-05","cited_by_count":7,"area":"deeprl"},{"id":"2410.11022","title":"Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning","created":"2024-10-14","cited_by_count":7,"area":"deeprl"},{"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":"2505.09371","title":"TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search","created":"2025-05-14","cited_by_count":7,"area":"deeprl"},{"id":"2505.15345","title":"Hadamax Encoding: Elevating Performance in Model-Free Atari","created":"2025-05-21","cited_by_count":7,"area":"deeprl"},{"id":"2510.21110","title":"Confounding Robust Deep Reinforcement Learning: A Causal Approach","created":"2025-10-24","cited_by_count":7,"area":"deeprl"},{"id":"2402.09900","title":"Recurrent Reinforcement Learning with Memoroids","created":"2024-02-15","cited_by_count":6,"area":"deeprl"},{"id":"2402.10228","title":"Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent","created":"2024-02-05","cited_by_count":6,"area":"deeprl"},{"id":"2402.16609","title":"Combining Transformer based Deep Reinforcement Learning with Black-Litterman Model for Portfolio Optimization","created":"2024-02-23","cited_by_count":6,"area":"deeprl"},{"id":"2403.02107","title":"Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning","created":"2024-03-04","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":"2406.16979","title":"Understanding and Diagnosing Deep Reinforcement Learning","created":"2024-06-23","cited_by_count":6,"area":"deeprl"},{"id":"2501.09080","title":"Average-Reward Soft Actor-Critic","created":"2025-01-15","cited_by_count":6,"area":"deeprl"},{"id":"2410.01431","title":"Scalable Reinforcement Learning-based Neural Architecture Search","created":"2024-10-02","cited_by_count":5,"area":"deeprl"},{"id":"2503.14555","title":"A Generalist Hanabi Agent","created":"2025-03-17","cited_by_count":5,"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":"2406.00887","title":"Deep Reinforcement Learning for Sim-to-Real Policy Transfer of VTOL-UAVs Offshore Docking Operations","created":"2024-06-02","cited_by_count":4,"area":"deeprl"},{"id":"2409.15866","title":"Online Planning for Multi-UAV Pursuit-Evasion in Unknown Environments Using Deep Reinforcement Learning","created":"2024-09-24","cited_by_count":4,"area":"deeprl"},{"id":"2412.02316","title":"Optimizing Plastic Waste Collection in Water Bodies Using Heterogeneous Autonomous Surface Vehicles with Deep Reinforcement Learning","created":"2024-12-03","cited_by_count":4,"area":"deeprl"},{"id":"2501.15034","title":"Divergence-Augmented Policy Optimization","created":"2025-01-25","cited_by_count":4,"area":"deeprl"},{"id":"2602.08690","title":"SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity","created":"2026-02-09","cited_by_count":4,"area":"deeprl"},{"id":"2403.01013","title":"A Holistic Power Optimization Approach for Microgrid Control Based on Deep Reinforcement Learning","created":"2024-03-01","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":"2409.02714","title":"MOOSS: Mask-Enhanced Temporal Contrastive Learning for Smooth State Evolution in Visual Reinforcement Learning","created":"2024-09-02","cited_by_count":3,"area":"deeprl"},{"id":"2501.04538","title":"HypeRL: Hypernetwork-Based Reinforcement Learning for Control of Parametrized Dynamical Systems","created":"2025-01-08","cited_by_count":3,"area":"deeprl"},{"id":"2503.12036","title":"Hierarchical Reinforcement Learning for Safe Mapless Navigation with Congestion Estimation","created":"2025-03-15","cited_by_count":3,"area":"deeprl"},{"id":"2402.09290","title":"Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning","created":"2024-02-14","cited_by_count":2,"area":"deeprl"},{"id":"2403.20163","title":"Biologically-Plausible Topology Improved Spiking Actor Network for Efficient Deep Reinforcement Learning","created":"2024-03-29","cited_by_count":2,"area":"deeprl"},{"id":"2406.14951","title":"An Idiosyncrasy of Time-discretization in Reinforcement Learning","created":"2024-06-21","cited_by_count":2,"area":"deeprl"},{"id":"2407.18840","title":"The Cross-environment Hyperparameter Setting Benchmark for Reinforcement Learning","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2409.14178","title":"FlowRL: Flow-Augmented Few-Shot Reinforcement Learning for Semi-Structured Sensor Data","created":"2024-09-21","cited_by_count":2,"area":"deeprl"},{"id":"2410.05425","title":"Designing a Classifier for Active Fire Detection from Multispectral Satellite Imagery Using Neural Architecture Search","created":"2024-10-07","cited_by_count":2,"area":"deeprl"},{"id":"2412.04847","title":"Enabling Energy-Efficient Simultaneous Multi-Task Reinforcement Learning through Spiking Neural Networks with Active Dendrites for Bio-inspired Generalist Agents","created":"2024-12-06","cited_by_count":2,"area":"deeprl"},{"id":"2503.20688","title":"Graph-Enhanced Model-Free Reinforcement Learning Agents for Efficient Power Grid Topological Control","created":"2025-03-26","cited_by_count":2,"area":"deeprl"},{"id":"2504.05521","title":"Deep Reinforcement Learning Algorithms for Option Hedging","created":"2025-04-07","cited_by_count":2,"area":"deeprl"},{"id":"2504.19499","title":"Graph Reinforcement Learning for QoS-Aware Load Balancing in Open Radio Access Networks","created":"2025-04-28","cited_by_count":2,"area":"deeprl"},{"id":"2505.20889","title":"Reinforcement Learning-based Sequential Route Recommendation for System-Optimal Traffic Assignment","created":"2025-05-27","cited_by_count":2,"area":"deeprl"},{"id":"2506.06410","title":"Delphos: A reinforcement learning framework for assisting discrete choice model specification","created":"2025-06-06","cited_by_count":2,"area":"deeprl"},{"id":"2506.06954","title":"Safety-Aware Reinforcement Learning for Control via Risk-Sensitive Action-Value Iteration and Quantile Regression","created":"2025-06-08","cited_by_count":2,"area":"deeprl"},{"id":"2507.09523","title":"An Analysis of Action-Value Temporal-Difference Methods That Learn State Values","created":"2025-07-13","cited_by_count":2,"area":"deeprl"},{"id":"2507.12189","title":"BenchRL-QAS: Benchmarking reinforcement learning algorithms for quantum architecture search","created":"2025-07-16","cited_by_count":2,"area":"deeprl"},{"id":"2509.14585","title":"Online reinforcement learning via sparse Gaussian mixture model Q-functions","created":"2025-09-18","cited_by_count":2,"area":"deeprl"},{"id":"2605.03434","title":"Quantum Hierarchical Reinforcement Learning via Variational Quantum Circuits","created":"2026-05-05","cited_by_count":2,"area":"deeprl"},{"id":"2402.00313","title":"Control in Stochastic Environment with Delays: A Model-based Reinforcement Learning Approach","created":"2024-02-01","cited_by_count":1,"area":"deeprl"},{"id":"2402.08491","title":"Deep Reinforcement Learning for Controlled Traversing of the Attractor Landscape of Boolean Models in the Context of Cellular Reprogramming","created":"2024-02-13","cited_by_count":1,"area":"deeprl"},{"id":"2402.14236","title":"Automated Design and Optimization of Distributed Filtering Circuits via Reinforcement Learning","created":"2024-02-22","cited_by_count":1,"area":"deeprl"},{"id":"2403.04453","title":"Efficient Off-Policy Learning for High-Dimensional Action Spaces","created":"2024-03-07","cited_by_count":1,"area":"deeprl"},{"id":"2405.09086","title":"Chaos-based reinforcement learning with TD3","created":"2024-05-15","cited_by_count":1,"area":"deeprl"},{"id":"2406.01838","title":"Learning the Target Network in Function Space","created":"2024-06-03","cited_by_count":1,"area":"deeprl"},{"id":"2408.06803","title":"Integrating Saliency Ranking and Reinforcement Learning for Enhanced Object Detection","created":"2024-08-13","cited_by_count":1,"area":"deeprl"},{"id":"2408.07712","title":"Introduction to Reinforcement Learning","created":"2024-08-13","cited_by_count":1,"area":"deeprl"},{"id":"2409.08815","title":"Deep reinforcement learning for tracking a moving target in jellyfish-like swimming","created":"2024-09-13","cited_by_count":1,"area":"deeprl"},{"id":"2410.19834","title":"GNNRL-Smoothing: A Prior-Free Reinforcement Learning Model for Mesh Smoothing","created":"2024-10-19","cited_by_count":1,"area":"deeprl"},{"id":"2410.23393","title":"Resource Governance in Networked Systems via Integrated Variational Autoencoders and Reinforcement Learning","created":"2024-10-30","cited_by_count":1,"area":"deeprl"},{"id":"2503.04219","title":"Quantum-Inspired Reinforcement Learning in the Presence of Epistemic Ambivalence","created":"2025-03-06","cited_by_count":1,"area":"deeprl"},{"id":"2504.11118","title":"Revealing Human Attention Patterns from Gameplay Analysis for Reinforcement Learning","created":"2025-04-15","cited_by_count":1,"area":"deeprl"},{"id":"2505.06319","title":"Reinforcement Learning for Game-Theoretic Resource Allocation on Graphs","created":"2025-05-08","cited_by_count":1,"area":"deeprl"},{"id":"2507.00275","title":"Deep Double Q-learning","created":"2025-06-30","cited_by_count":1,"area":"deeprl"},{"id":"2507.11726","title":"A Deep Reinforcement Learning Method for Multi-objective Transmission Switching","created":"2025-07-15","cited_by_count":1,"area":"deeprl"},{"id":"2508.07452","title":"Stackelberg Coupling of Online Representation Learning and Reinforcement Learning","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2509.02861","title":"Power Grid Control with Graph-Based Distributed Reinforcement Learning","created":"2025-09-02","cited_by_count":1,"area":"deeprl"},{"id":"2512.18763","title":"Gaussian-Mixture-Model Q-Functions for Policy Iteration in Reinforcement Learning","created":"2025-12-21","cited_by_count":1,"area":"deeprl"},{"id":"2601.02850","title":"Sample-Efficient Neurosymbolic Deep Reinforcement Learning","created":"2026-01-06","cited_by_count":1,"area":"deeprl"},{"id":"2603.15871","title":"Counteractive RL: Rethinking Core Principles for Efficient and Scalable Deep Reinforcement Learning","created":"2026-03-16","cited_by_count":1,"area":"deeprl"},{"id":"2603.26816","title":"PiCSRL: Physics-Informed Contextual Spectral Reinforcement Learning","created":"2026-03-26","cited_by_count":1,"area":"deeprl"},{"id":"2606.20411","title":"Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning","created":"2026-06-18","cited_by_count":1,"area":"deeprl"},{"id":"2401.04145","title":"Learn Once Plan Arbitrarily (LOPA): Attention-Enhanced Deep Reinforcement Learning Method for Global Path Planning","created":"2024-01-08","cited_by_count":0,"area":"deeprl"},{"id":"2401.09772","title":"Robotic Test Tube Rearrangement Using Combined Reinforcement Learning and Motion Planning","created":"2024-01-18","cited_by_count":0,"area":"deeprl"},{"id":"2402.03329","title":"Unsupervised Salient Patch Selection for Data-Efficient Reinforcement Learning","created":"2024-01-10","cited_by_count":0,"area":"deeprl"},{"id":"2402.11835","title":"Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret Minimization","created":"2024-02-19","cited_by_count":0,"area":"deeprl"},{"id":"2403.03643","title":"A Survey on Applications of Reinforcement Learning in Spatial Resource Allocation","created":"2024-03-06","cited_by_count":0,"area":"deeprl"},{"id":"2403.07566","title":"An Improved Strategy for Blood Glucose Control Using Multi-Step Deep Reinforcement Learning","created":"2024-03-12","cited_by_count":0,"area":"deeprl"},{"id":"2403.17542","title":"VDSC: Enhancing Exploration Timing with Value Discrepancy and State Counts","created":"2024-03-26","cited_by_count":0,"area":"deeprl"},{"id":"2404.00686","title":"Utilizing Maximum Mean Discrepancy Barycenter for Propagating the Uncertainty of Value Functions in Reinforcement Learning","created":"2024-03-31","cited_by_count":0,"area":"deeprl"},{"id":"2404.01557","title":"Distributed Autonomous Swarm Formation for Dynamic Network Bridging","created":"2024-04-02","cited_by_count":0,"area":"deeprl"},{"id":"2404.08523","title":"Advancing Forest Fire Prevention: Deep Reinforcement Learning for Effective Firebreak Placement","created":"2024-04-12","cited_by_count":0,"area":"deeprl"},{"id":"2405.13960","title":"Learning To Play Atari Games Using Dueling Q-Learning and Hebbian Plasticity","created":"2024-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2405.16485","title":"Make Safe Decisions in Power System: Safe Reinforcement Learning Based Pre-decision Making for Voltage Stability Emergency Control","created":"2024-05-26","cited_by_count":0,"area":"deeprl"},{"id":"2405.18761","title":"FDQN: A Flexible Deep Q-Network Framework for Game Automation","created":"2024-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2406.05041","title":"Online Frequency Scheduling by Learning Parallel Actions","created":"2024-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2407.11044","title":"Generalizing soft actor-critic algorithms to discrete action spaces","created":"2024-07-08","cited_by_count":0,"area":"deeprl"},{"id":"2407.16377","title":"Reinforcement Learning-based Adaptive Mitigation of Uncorrected DRAM Errors in the Field","created":"2024-07-23","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}