{"total":172,"rows":[{"id":"2403.00514","title":"Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning","created":"2024-03-01","cited_by_count":50,"area":"deeprl"},{"id":"2502.20396","title":"Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids","created":"2025-02-27","cited_by_count":48,"area":"deeprl"},{"id":"2407.17032","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","created":"2024-07-24","cited_by_count":46,"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":"2504.17838","title":"CaRL: Learning Scalable Planning Policies with Simple Rewards","created":"2025-04-24","cited_by_count":35,"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":"2408.01072","title":"A Survey on Self-play Methods in Reinforcement Learning","created":"2024-08-02","cited_by_count":26,"area":"deeprl"},{"id":"2411.04832","title":"Plasticity Loss in Deep Reinforcement Learning: A Survey","created":"2024-11-07","cited_by_count":24,"area":"deeprl"},{"id":"2405.19014","title":"Trust the Model Where It Trusts Itself -- Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption","created":"2024-05-29","cited_by_count":18,"area":"deeprl"},{"id":"2410.01312","title":"Sampling from Energy-based Policies using Diffusion","created":"2024-10-02","cited_by_count":17,"area":"deeprl"},{"id":"2406.16241","title":"Position: Benchmarking is Limited in Reinforcement Learning Research","created":"2024-06-23","cited_by_count":15,"area":"deeprl"},{"id":"2409.18197","title":"Autonomous Network Defence using Reinforcement Learning","created":"2024-09-26","cited_by_count":15,"area":"deeprl"},{"id":"2405.17416","title":"A Recipe for Unbounded Data Augmentation in Visual Reinforcement Learning","created":"2024-05-27","cited_by_count":14,"area":"deeprl"},{"id":"2410.22391","title":"A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks","created":"2024-10-29","cited_by_count":14,"area":"deeprl"},{"id":"2505.24061","title":"Measure gradients, not activations! Enhancing neuronal activity in deep reinforcement learning","created":"2025-05-29","cited_by_count":14,"area":"deeprl"},{"id":"2407.08590","title":"A Review of Nine Physics Engines for Reinforcement Learning Research","created":"2024-07-11","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":"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":"2402.03141","title":"Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays","created":"2024-02-05","cited_by_count":10,"area":"deeprl"},{"id":"2403.04344","title":"RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning","created":"2024-03-07","cited_by_count":10,"area":"deeprl"},{"id":"2405.00629","title":"HUGO -- Highlighting Unseen Grid Options: Combining Deep Reinforcement Learning with a Heuristic Target Topology Approach","created":"2024-05-01","cited_by_count":10,"area":"deeprl"},{"id":"2405.19697","title":"Bilevel reinforcement learning via the development of hyper-gradient without lower-level convexity","created":"2024-05-30","cited_by_count":10,"area":"deeprl"},{"id":"2407.04315","title":"Gradient-based Regularization for Action Smoothness in Robotic Control with Reinforcement Learning","created":"2024-07-05","cited_by_count":10,"area":"deeprl"},{"id":"2501.16918","title":"On Rollouts in Model-Based Reinforcement Learning","created":"2025-01-28","cited_by_count":10,"area":"deeprl"},{"id":"2501.19400","title":"Vintix: Action Model via In-Context Reinforcement Learning","created":"2025-01-31","cited_by_count":10,"area":"deeprl"},{"id":"2510.04786","title":"Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning","created":"2025-10-06","cited_by_count":9,"area":"deeprl"},{"id":"2402.01361","title":"To the Max: Reinventing Reward in Reinforcement Learning","created":"2024-02-02","cited_by_count":8,"area":"deeprl"},{"id":"2402.10033","title":"Neural Network Approaches for Parameterized Optimal Control","created":"2024-02-15","cited_by_count":8,"area":"deeprl"},{"id":"2404.18326","title":"SAFE-RL: Saliency-Aware Counterfactual Explainer for Deep Reinforcement Learning Policies","created":"2024-04-28","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":"2402.03590","title":"Assessing the Impact of Distribution Shift on Reinforcement Learning Performance","created":"2024-02-05","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":"2503.00496","title":"Flying on Point Clouds with Reinforcement Learning","created":"2025-03-01","cited_by_count":7,"area":"deeprl"},{"id":"2402.18866","title":"Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming","created":"2024-02-29","cited_by_count":6,"area":"deeprl"},{"id":"2405.18180","title":"Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding","created":"2024-05-28","cited_by_count":6,"area":"deeprl"},{"id":"2503.08241","title":"HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents","created":"2025-03-11","cited_by_count":6,"area":"deeprl"},{"id":"2506.09270","title":"Uncertainty Prioritized Experience Replay","created":"2025-06-10","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":"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":"2403.19448","title":"Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients","created":"2024-03-28","cited_by_count":5,"area":"deeprl"},{"id":"2405.12800","title":"Deep Reinforcement Learning for Time-Critical Wilderness Search And Rescue Using Drones","created":"2024-05-21","cited_by_count":5,"area":"deeprl"},{"id":"2406.11810","title":"Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics","created":"2024-06-17","cited_by_count":5,"area":"deeprl"},{"id":"2406.19768","title":"Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors","created":"2024-06-28","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":"2604.25416","title":"Biased Dreams: Limitations to Epistemic Uncertainty Quantification in Latent Dynamics Models","created":"2026-04-28","cited_by_count":5,"area":"deeprl"},{"id":"2407.15168","title":"Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space","created":"2024-07-21","cited_by_count":4,"area":"deeprl"},{"id":"2501.03888","title":"Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policies","created":"2025-01-07","cited_by_count":4,"area":"deeprl"},{"id":"2503.19037","title":"Evolutionary Policy Optimization","created":"2025-03-24","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":"2404.04772","title":"Efficient Reinforcement Learning of Task Planners for Robotic Palletization through Iterative Action Masking Learning","created":"2024-04-07","cited_by_count":3,"area":"deeprl"},{"id":"2406.07980","title":"Reinforcement Learning for High-Level Strategic Control in Tower Defense Games","created":"2024-06-12","cited_by_count":3,"area":"deeprl"},{"id":"2407.15083","title":"Rocket Landing Control with Random Annealing Jump Start Reinforcement Learning","created":"2024-07-21","cited_by_count":3,"area":"deeprl"},{"id":"2409.10096","title":"Robust Reinforcement Learning with Dynamic Distortion Risk Measures","created":"2024-09-16","cited_by_count":3,"area":"deeprl"},{"id":"2410.02038","title":"Realizable Continuous-Space Shields for Safe Reinforcement Learning","created":"2024-10-02","cited_by_count":3,"area":"deeprl"},{"id":"2410.12197","title":"Potential-Based Intrinsic Motivation: Preserving Optimality With Complex, Non-Markovian Shaping Rewards","created":"2024-10-16","cited_by_count":3,"area":"deeprl"},{"id":"2411.00666","title":"Beyond the Boundaries of Proximal Policy Optimization","created":"2024-11-01","cited_by_count":3,"area":"deeprl"},{"id":"2507.06602","title":"Generalization in Reinforcement Learning for Radio Access Networks","created":"2025-07-09","cited_by_count":3,"area":"deeprl"},{"id":"2602.04809","title":"Beyond Rewards in Reinforcement Learning for Cyber Defence","created":"2026-02-04","cited_by_count":3,"area":"deeprl"},{"id":"2402.12034","title":"When Do Off-Policy and On-Policy Policy Gradient Methods Align?","created":"2024-02-19","cited_by_count":2,"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":"2404.14552","title":"Generalizing Multi-Step Inverse Models for Representation Learning to Finite-Memory POMDPs","created":"2024-04-22","cited_by_count":2,"area":"deeprl"},{"id":"2405.15421","title":"Model-free reinforcement learning with noisy actions for automated experimental control in optics","created":"2024-05-24","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":"2406.17168","title":"Reinforcement Learning via Auxiliary Task Distillation","created":"2024-06-24","cited_by_count":2,"area":"deeprl"},{"id":"2407.18597","title":"Reinforcement Learning for Sustainable Energy: A Survey","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2408.08230","title":"Explaining an Agent's Future Beliefs through Temporally Decomposing Future Reward Estimators","created":"2024-08-15","cited_by_count":2,"area":"deeprl"},{"id":"2408.08446","title":"Lifelong Reinforcement Learning via Neuromodulation","created":"2024-08-15","cited_by_count":2,"area":"deeprl"},{"id":"2411.11318","title":"Syllabus: Portable Curricula for Reinforcement Learning Agents","created":"2024-11-18","cited_by_count":2,"area":"deeprl"},{"id":"2504.02662","title":"Integrating Human Knowledge Through Action Masking in Reinforcement Learning for Operations Research","created":"2025-04-03","cited_by_count":2,"area":"deeprl"},{"id":"2504.03429","title":"Optimizing Quantum Circuits via ZX Diagrams using Reinforcement Learning and Graph Neural Networks","created":"2025-04-04","cited_by_count":2,"area":"deeprl"},{"id":"2507.07197","title":"Combining Pre-Trained Models for Enhanced Feature Representation in Reinforcement Learning","created":"2025-07-09","cited_by_count":2,"area":"deeprl"},{"id":"2509.20008","title":"Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation","created":"2025-09-24","cited_by_count":2,"area":"deeprl"},{"id":"2510.20314","title":"Enhancing Security in Deep Reinforcement Learning: A Comprehensive Survey on Adversarial Attacks and Defenses","created":"2025-10-23","cited_by_count":2,"area":"deeprl"},{"id":"2510.23216","title":"Human-Like Goalkeeping in a Realistic Football Simulation: a Sample-Efficient Reinforcement Learning Approach","created":"2025-10-27","cited_by_count":2,"area":"deeprl"},{"id":"2512.18957","title":"Online Robust Reinforcement Learning with General Function Approximation","created":"2025-12-22","cited_by_count":2,"area":"deeprl"},{"id":"2602.17098","title":"Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization","created":"2026-02-19","cited_by_count":2,"area":"deeprl"},{"id":"2604.01913","title":"The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning","created":"2026-04-02","cited_by_count":2,"area":"deeprl"},{"id":"2402.05187","title":"Learning mirror maps in policy mirror descent","created":"2024-02-07","cited_by_count":1,"area":"deeprl"},{"id":"2402.13582","title":"Mastering the Game of Guandan with Deep Reinforcement Learning and Behavior Regulating","created":"2024-02-21","cited_by_count":1,"area":"deeprl"},{"id":"2404.03336","title":"Benchmarking Population-Based Reinforcement Learning across Robotic Tasks with GPU-Accelerated Simulation","created":"2024-04-04","cited_by_count":1,"area":"deeprl"},{"id":"2404.07826","title":"On the Sample Efficiency of Abstractions and Potential-Based Reward Shaping in Reinforcement Learning","created":"2024-04-11","cited_by_count":1,"area":"deeprl"},{"id":"2409.03301","title":"ELO-Rated Sequence Rewards: Advancing Reinforcement Learning Models","created":"2024-09-05","cited_by_count":1,"area":"deeprl"},{"id":"2410.17517","title":"The Hive Mind is a Single Reinforcement Learning Agent","created":"2024-10-23","cited_by_count":1,"area":"deeprl"},{"id":"2501.04068","title":"Explainable Reinforcement Learning for Formula One Race Strategy","created":"2025-01-07","cited_by_count":1,"area":"deeprl"},{"id":"2502.13392","title":"Atomic Proximal Policy Optimization for Electric Robo-Taxi Dispatch and Charger Allocation","created":"2025-02-19","cited_by_count":1,"area":"deeprl"},{"id":"2502.17983","title":"Provable Performance Bounds for Digital Twin-driven Deep Reinforcement Learning in Wireless Networks: A Novel Digital-Twin Bisimulation Metric","created":"2025-02-25","cited_by_count":1,"area":"deeprl"},{"id":"2502.19920","title":"Pokemon Red via Reinforcement Learning","created":"2025-02-27","cited_by_count":1,"area":"deeprl"},{"id":"2503.00345","title":"Towards Understanding the Benefit of Multitask Representation Learning in Decision Process","created":"2025-03-01","cited_by_count":1,"area":"deeprl"},{"id":"2503.05092","title":"Multi-Robot Collaboration through Reinforcement Learning and Abstract Simulation","created":"2025-03-07","cited_by_count":1,"area":"deeprl"},{"id":"2504.21731","title":"Adaptive 3D UI Placement in Mixed Reality Using Deep Reinforcement Learning","created":"2025-04-30","cited_by_count":1,"area":"deeprl"},{"id":"2505.19058","title":"Distributionally Robust Deep Q-Learning","created":"2025-05-25","cited_by_count":1,"area":"deeprl"},{"id":"2506.11706","title":"Growing with Experience: Growing Neural Networks in Deep Reinforcement Learning","created":"2025-06-13","cited_by_count":1,"area":"deeprl"},{"id":"2507.06825","title":"Artificial Generals Intelligence: Mastering Generals.io with Reinforcement Learning","created":"2025-07-09","cited_by_count":1,"area":"deeprl"},{"id":"2508.01329","title":"Is Exploration or Optimization the Problem for Deep Reinforcement Learning?","created":"2025-08-02","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":"2510.20542","title":"A Unified Framework for Zero-Shot Reinforcement Learning","created":"2025-10-23","cited_by_count":1,"area":"deeprl"},{"id":"2511.07831","title":"Distributionally Robust Online Markov Game with Linear Function Approximation","created":"2025-11-11","cited_by_count":1,"area":"deeprl"},{"id":"2601.14957","title":"Improving Regret Approximation for Unsupervised Dynamic Environment Generation","created":"2026-01-21","cited_by_count":1,"area":"deeprl"},{"id":"2602.10598","title":"Neuro-symbolic Action Masking for Deep Reinforcement Learning","created":"2026-02-11","cited_by_count":1,"area":"deeprl"}],"next_cursor":"100"}