{"total":49,"rows":[{"id":"2407.17032","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","created":"2024-07-24","cited_by_count":46,"area":"deeprl"},{"id":"2407.01704","title":"Weight Clipping for Deep Continual and Reinforcement Learning","created":"2024-07-01","cited_by_count":29,"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":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17,"area":"deeprl"},{"id":"2502.08938","title":"Reevaluating Policy Gradient Methods for Imperfect-Information Games","created":"2025-02-13","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":"2401.12497","title":"Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning","created":"2024-01-23","cited_by_count":11,"area":"deeprl"},{"id":"2501.15893","title":"Benchmarking Quantum Reinforcement Learning","created":"2025-01-27","cited_by_count":10,"area":"deeprl"},{"id":"2402.15164","title":"EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender Systems","created":"2024-02-23","cited_by_count":9,"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":"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":"2405.03064","title":"RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation","created":"2024-05-05","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":"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":"2412.00744","title":"Open-World Drone Active Tracking with Goal-Centered Rewards","created":"2024-12-01","cited_by_count":6,"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":"2409.05344","title":"GOPT: Generalizable Online 3D Bin Packing via Transformer-based Deep Reinforcement Learning","created":"2024-09-09","cited_by_count":4,"area":"deeprl"},{"id":"2507.11060","title":"Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing","created":"2025-07-15","cited_by_count":4,"area":"deeprl"},{"id":"2501.00913","title":"$\\beta$-DQN: Improving Deep Q-Learning By Evolving the Behavior","created":"2025-01-01","cited_by_count":3,"area":"deeprl"},{"id":"2603.06413","title":"A Reference Architecture of Reinforcement Learning Frameworks","created":"2026-03-06","cited_by_count":3,"area":"deeprl"},{"id":"2402.00972","title":"Closure Discovery for Coarse-Grained Partial Differential Equations Using Grid-based Reinforcement Learning","created":"2024-02-01","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":"2406.04920","title":"Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning","created":"2024-06-07","cited_by_count":2,"area":"deeprl"},{"id":"2412.09466","title":"Distributional Reinforcement Learning based Integrated Decision Making and Control for Autonomous Surface Vehicles","created":"2024-12-12","cited_by_count":2,"area":"deeprl"},{"id":"2501.19128","title":"Shaping Sparse Rewards in Reinforcement Learning: A Semi-supervised Approach","created":"2025-01-31","cited_by_count":2,"area":"deeprl"},{"id":"2404.14763","title":"Evolutionary Reinforcement Learning via Cooperative Coevolution","created":"2024-04-23","cited_by_count":1,"area":"deeprl"},{"id":"2410.16653","title":"Enhancing Two-Player Performance Through Single-Player Knowledge Transfer: An Empirical Study on Atari 2600 Games","created":"2024-10-22","cited_by_count":1,"area":"deeprl"},{"id":"2503.02269","title":"Experience Replay with Random Reshuffling","created":"2025-03-04","cited_by_count":1,"area":"deeprl"},{"id":"2504.10248","title":"Adaptive Sensor Steering Strategy Using Deep Reinforcement Learning for Dynamic Data Acquisition in Digital Twins","created":"2025-04-14","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":"2603.10199","title":"Actor-Accelerated Policy Dual Averaging for Reinforcement Learning in Continuous Action Spaces","created":"2026-03-10","cited_by_count":1,"area":"deeprl"},{"id":"2401.05969","title":"Spatial-Aware Deep Reinforcement Learning for the Traveling Officer Problem","created":"2024-01-11","cited_by_count":0,"area":"deeprl"},{"id":"2401.14488","title":"Scilab-RL: A software framework for efficient reinforcement learning and cognitive modeling research","created":"2024-01-25","cited_by_count":0,"area":"deeprl"},{"id":"2409.04971","title":"Soft Actor-Critic with Beta Policy via Implicit Reparameterization Gradients","created":"2024-09-08","cited_by_count":0,"area":"deeprl"},{"id":"2409.13620","title":"Subassembly to Full Assembly: Effective Assembly Sequence Planning through Graph-based Reinforcement Learning","created":"2024-09-20","cited_by_count":0,"area":"deeprl"},{"id":"2503.22575","title":"On the Mistaken Assumption of Interchangeable Deep Reinforcement Learning Implementations","created":"2025-03-28","cited_by_count":0,"area":"deeprl"},{"id":"2505.11308","title":"Reinforcement Learning Closures for Underresolved Partial Differential Equations using Synthetic Data","created":"2025-05-16","cited_by_count":0,"area":"deeprl"},{"id":"2505.21536","title":"CiRL: Open-Source Environments for Reinforcement Learning in Circular Economy and Net Zero","created":"2025-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2506.16795","title":"Robust Dynamic Material Handling via Adaptive Constrained Evolutionary Reinforcement Learning","created":"2025-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2507.03487","title":"ObjectRL: An Object-Oriented Reinforcement Learning Codebase","created":"2025-07-04","cited_by_count":0,"area":"deeprl"},{"id":"2507.10990","title":"Adaptive Policy Synchronization for Scalable Reinforcement Learning","created":"2025-07-15","cited_by_count":0,"area":"deeprl"},{"id":"2509.19159","title":"Efficient Reinforcement Learning by Reducing Forgetting with Elephant Activation Functions","created":"2025-09-23","cited_by_count":0,"area":"deeprl"},{"id":"2512.04095","title":"Quantum-Embedded Dynamic Security Control using Hybrid Deep Reinforcement Learning","created":"2025-11-21","cited_by_count":0,"area":"deeprl"},{"id":"2602.09726","title":"ExO-PPO: an Extended Off-policy Proximal Policy Optimization Algorithm","created":"2026-02-10","cited_by_count":0,"area":"deeprl"},{"id":"2603.07800","title":"Preference-Conditioned Reinforcement Learning for Space-Time Efficient Online 3D Bin Packing","created":"2026-03-08","cited_by_count":0,"area":"deeprl"},{"id":"2605.18454","title":"Scheduling That Speaks: An Interpretable Programmatic Reinforcement Learning Framework","created":"2026-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2605.18508","title":"DiPRL: Learning Discrete Programmatic Policies via Architecture Entropy Regularization","created":"2026-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2605.27385","title":"Personalized Observation Normalization for Federated Reinforcement Learning in Simulation Environments with Heterogeneity","created":"2026-04-10","cited_by_count":0,"area":"deeprl"},{"id":"2608.04590","title":"Joint UAV Flight and Opportunistic Routing under Reinforcement Learning for Delay-Tolerant Networks","created":"2026-08-05","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}