{"total":431,"rows":[{"id":"2410.09754","title":"SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learning","created":"2024-10-13","cited_by_count":76,"area":"deeprl"},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"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":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"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":"2403.02131","title":"Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution","created":"2024-03-04","cited_by_count":24,"area":"deeprl"},{"id":"2401.05821","title":"Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents","created":"2024-01-11","cited_by_count":23,"area":"deeprl"},{"id":"2506.15544","title":"Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning","created":"2025-06-18","cited_by_count":23,"area":"deeprl"},{"id":"2506.00592","title":"Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn","created":"2025-05-31","cited_by_count":22,"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":"2501.06773","title":"Pareto Set Learning for Multi-Objective Reinforcement Learning","created":"2025-01-12","cited_by_count":20,"area":"deeprl"},{"id":"2405.14956","title":"Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning","created":"2024-05-23","cited_by_count":18,"area":"deeprl"},{"id":"2407.19396","title":"NAVIX: Scaling MiniGrid Environments with JAX","created":"2024-07-28","cited_by_count":18,"area":"deeprl"},{"id":"2411.15370","title":"Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers","created":"2024-11-22","cited_by_count":18,"area":"deeprl"},{"id":"2403.05996","title":"Dissecting Deep RL with High Update Ratios: Combatting Value Divergence","created":"2024-03-09","cited_by_count":17,"area":"deeprl"},{"id":"2409.04792","title":"Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn","created":"2024-09-07","cited_by_count":17,"area":"deeprl"},{"id":"2402.14528","title":"ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization","created":"2024-02-22","cited_by_count":16,"area":"deeprl"},{"id":"2404.06492","title":"Graph Reinforcement Learning for Combinatorial Optimization: A Survey and Unifying Perspective","created":"2024-04-09","cited_by_count":16,"area":"deeprl"},{"id":"2503.03660","title":"Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns","created":"2025-03-05","cited_by_count":16,"area":"deeprl"},{"id":"2403.14508","title":"Constrained Reinforcement Learning with Smoothed Log Barrier Function","created":"2024-03-21","cited_by_count":15,"area":"deeprl"},{"id":"2510.07650","title":"Value Flows","created":"2025-10-09","cited_by_count":15,"area":"deeprl"},{"id":"2406.17718","title":"When does Self-Prediction help? Understanding Auxiliary Tasks in Reinforcement Learning","created":"2024-06-25","cited_by_count":14,"area":"deeprl"},{"id":"2407.20147","title":"Quantum Machine Learning Architecture Search via Deep Reinforcement Learning","created":"2024-07-29","cited_by_count":13,"area":"deeprl"},{"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":"2503.18061","title":"Reinforcement Learning-based Self-adaptive Differential Evolution through Automated Landscape Feature Learning","created":"2025-03-23","cited_by_count":12,"area":"deeprl"},{"id":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","cited_by_count":12,"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":"2408.10932","title":"The Evolution of Reinforcement Learning in Quantitative Finance: A Survey","created":"2024-08-20","cited_by_count":11,"area":"deeprl"},{"id":"2405.18520","title":"Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL","created":"2024-05-28","cited_by_count":10,"area":"deeprl"},{"id":"2501.15893","title":"Benchmarking Quantum Reinforcement Learning","created":"2025-01-27","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":"2405.17358","title":"Rethinking Transformers in Solving POMDPs","created":"2024-05-27","cited_by_count":9,"area":"deeprl"},{"id":"2407.13743","title":"Optimistic Q-learning for average reward and episodic reinforcement learning","created":"2024-07-18","cited_by_count":9,"area":"deeprl"},{"id":"2503.23101","title":"RL2Grid: Benchmarking Reinforcement Learning in Power Grid Operations","created":"2025-03-29","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":"2403.20020","title":"Nonparametric Bellman Mappings for Reinforcement Learning: Application to Robust Adaptive Filtering","created":"2024-03-29","cited_by_count":8,"area":"deeprl"},{"id":"2404.07450","title":"Collaborative Ground-Space Communications via Evolutionary Multi-objective Deep Reinforcement Learning","created":"2024-04-11","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":"2512.24288","title":"Real-world Reinforcement Learning from Suboptimal Interventions","created":"2025-12-30","cited_by_count":8,"area":"deeprl"},{"id":"2402.05284","title":"Analyzing Adversarial Inputs in Deep Reinforcement Learning","created":"2024-02-07","cited_by_count":7,"area":"deeprl"},{"id":"2403.10859","title":"Neural-Kernel Conditional Mean Embeddings","created":"2024-03-16","cited_by_count":7,"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":"2404.04253","title":"Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution","created":"2024-04-05","cited_by_count":7,"area":"deeprl"},{"id":"2406.01423","title":"Value Improved Actor Critic Algorithms","created":"2024-06-03","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":"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":"2501.08669","title":"SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning","created":"2025-01-15","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":"2505.09371","title":"TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search","created":"2025-05-14","cited_by_count":7,"area":"deeprl"},{"id":"2505.15211","title":"GCNT: Graph-Based Transformer Policies for Morphology-Agnostic Reinforcement Learning","created":"2025-05-21","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":"2401.08850","title":"REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes","created":"2024-01-16","cited_by_count":6,"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":"2402.15790","title":"Discretionary Lane-Change Decision and Control via Parameterized Soft Actor-Critic for Hybrid Action Space","created":"2024-02-24","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":"2405.04342","title":"The Curse of Diversity in Ensemble-Based Exploration","created":"2024-05-07","cited_by_count":6,"area":"deeprl"},{"id":"2405.12308","title":"Continual Deep Reinforcement Learning for Decentralized Satellite Routing","created":"2024-05-20","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":"2407.06121","title":"Periodic agent-state based Q-learning for POMDPs","created":"2024-07-08","cited_by_count":6,"area":"deeprl"},{"id":"2410.03376","title":"Mitigating Adversarial Perturbations for Deep Reinforcement Learning via Vector Quantization","created":"2024-10-04","cited_by_count":6,"area":"deeprl"},{"id":"2412.10917","title":"Adaptive Reward Design for Reinforcement Learning","created":"2024-12-14","cited_by_count":6,"area":"deeprl"},{"id":"2503.05546","title":"Impoola: The Power of Average Pooling for Image-Based Deep Reinforcement Learning","created":"2025-03-07","cited_by_count":6,"area":"deeprl"},{"id":"2506.13672","title":"The Courage to Stop: Overcoming Sunk Cost Fallacy in Deep Reinforcement Learning","created":"2025-06-16","cited_by_count":6,"area":"deeprl"},{"id":"2601.21306","title":"The Surprising Difficulty of Search in Model-Based Reinforcement Learning","created":"2026-01-29","cited_by_count":6,"area":"deeprl"},{"id":"2402.05476","title":"Multi-Timescale Ensemble Q-learning for Markov Decision Process Policy Optimization","created":"2024-02-08","cited_by_count":5,"area":"deeprl"},{"id":"2402.17773","title":"SINR-Aware Deep Reinforcement Learning for Distributed Dynamic Channel Allocation in Cognitive Interference Networks","created":"2024-02-17","cited_by_count":5,"area":"deeprl"},{"id":"2405.02576","title":"CTD4 -- A Deep Continuous Distributional Actor-Critic Agent with a Kalman Fusion of Multiple Critics","created":"2024-05-04","cited_by_count":5,"area":"deeprl"},{"id":"2405.10310","title":"Stochastic Q-learning for Large Discrete Action Spaces","created":"2024-05-16","cited_by_count":5,"area":"deeprl"},{"id":"2411.06389","title":"Optimal Execution with Reinforcement Learning","created":"2024-11-10","cited_by_count":5,"area":"deeprl"},{"id":"2502.20265","title":"On the Importance of Reward Design in Reinforcement Learning-based Dynamic Algorithm Configuration: A Case Study on OneMax with (1+($\\lambda$,$\\lambda$))-GA","created":"2025-02-27","cited_by_count":5,"area":"deeprl"},{"id":"2503.01919","title":"Reinforcement learning with combinatorial actions for coupled restless bandits","created":"2025-03-01","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":"2505.19247","title":"Improving Value Estimation Critically Enhances Vanilla Policy Gradient","created":"2025-05-25","cited_by_count":5,"area":"deeprl"},{"id":"2511.03279","title":"Multi-Objective Adaptive Rate Limiting in Microservices Using Deep Reinforcement Learning","created":"2025-11-05","cited_by_count":5,"area":"deeprl"},{"id":"2401.03197","title":"Decision Making in Non-Stationary Environments with Policy-Augmented Search","created":"2024-01-06","cited_by_count":4,"area":"deeprl"},{"id":"2401.13447","title":"Symbolic Equation Solving via Reinforcement Learning","created":"2024-01-24","cited_by_count":4,"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":"2405.04017","title":"An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks","created":"2024-05-07","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":"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":"2407.18110","title":"MapTune: Advancing ASIC Technology Mapping via Reinforcement Learning Guided Library Tuning","created":"2024-07-25","cited_by_count":4,"area":"deeprl"},{"id":"2412.02291","title":"Conformal Symplectic Optimization for Stable Reinforcement Learning","created":"2024-12-03","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":"2501.07445","title":"Online inductive learning from answer sets for efficient reinforcement learning exploration","created":"2025-01-13","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":"2503.09270","title":"Rule-Guided Reinforcement Learning Policy Evaluation and Improvement","created":"2025-03-12","cited_by_count":4,"area":"deeprl"},{"id":"2506.01016","title":"Optimistic critics can empower small actors","created":"2025-06-01","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":"2601.19720","title":"Improving Policy Exploitation in Online Reinforcement Learning with Instant Retrospect Action","created":"2026-01-27","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":"2403.06366","title":"Finite-Time Error Analysis of Soft Q-Learning: Switching System Approach","created":"2024-03-11","cited_by_count":3,"area":"deeprl"},{"id":"2404.08161","title":"R2 Indicator and Deep Reinforcement Learning Enhanced Adaptive Multi-Objective Evolutionary Algorithm","created":"2024-04-11","cited_by_count":3,"area":"deeprl"},{"id":"2406.02057","title":"Tabular and Deep Learning for the Whittle Index","created":"2024-06-04","cited_by_count":3,"area":"deeprl"},{"id":"2406.03678","title":"Reflective Policy Optimization","created":"2024-06-06","cited_by_count":3,"area":"deeprl"}],"next_cursor":"100"}