{"total":73,"rows":[{"id":"2406.03704","title":"Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking","created":"2024-06-06","cited_by_count":19,"area":"deeprl"},{"id":"2405.20579","title":"HOPE: A Reinforcement Learning-based Hybrid Policy Path Planner for Diverse Parking Scenarios","created":"2024-05-31","cited_by_count":11,"area":"deeprl"},{"id":"2402.00046","title":"Introducing PetriRL: An Innovative Framework for JSSP Resolution Integrating Petri nets and Event-based Reinforcement Learning","created":"2024-01-23","cited_by_count":6,"area":"deeprl"},{"id":"2412.04327","title":"Action Mapping for Reinforcement Learning in Continuous Environments with Constraints","created":"2024-12-05","cited_by_count":5,"area":"deeprl"},{"id":"2502.14372","title":"Discovering highly efficient low-weight quantum error-correcting codes with reinforcement learning","created":"2025-02-20","cited_by_count":5,"area":"deeprl"},{"id":"2403.05787","title":"Scaling Team Coordination on Graphs with Reinforcement Learning","created":"2024-03-09","cited_by_count":3,"area":"deeprl"},{"id":"2409.16882","title":"Revisiting Space Mission Planning: A Reinforcement Learning-Guided Approach for Multi-Debris Rendezvous","created":"2024-09-25","cited_by_count":3,"area":"deeprl"},{"id":"2402.08112","title":"A Competition Winning Deep Reinforcement Learning Agent in microRTS","created":"2024-02-12","cited_by_count":2,"area":"deeprl"},{"id":"2409.18574","title":"Climate Adaptation with Reinforcement Learning: Experiments with Flooding and Transportation in Copenhagen","created":"2024-09-27","cited_by_count":2,"area":"deeprl"},{"id":"2503.03208","title":"Embodied Escaping: End-to-End Reinforcement Learning for Robot Navigation in Narrow Environment","created":"2025-03-05","cited_by_count":2,"area":"deeprl"},{"id":"2503.17985","title":"Optimizing Navigation And Chemical Application in Precision Agriculture With Deep Reinforcement Learning And Conditional Action Tree","created":"2025-03-23","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":"2504.02662","title":"Integrating Human Knowledge Through Action Masking in Reinforcement Learning for Operations Research","created":"2025-04-03","cited_by_count":2,"area":"deeprl"},{"id":"2504.12045","title":"pix2pockets: Shot Suggestions in 8-Ball Pool from a Single Image in the Wild","created":"2025-04-16","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":"2509.01838","title":"Goal-Conditioned Reinforcement Learning for Data-Driven Maritime Navigation","created":"2025-09-01","cited_by_count":2,"area":"deeprl"},{"id":"2511.22321","title":"RELiQ: Scalable Entanglement Routing via Reinforcement Learning in Quantum Networks","created":"2025-11-27","cited_by_count":2,"area":"deeprl"},{"id":"2401.17976","title":"Circuit Partitioning for Multi-Core Quantum Architectures with Deep Reinforcement Learning","created":"2024-01-31","cited_by_count":1,"area":"deeprl"},{"id":"2404.02577","title":"Solving a Real-World Optimization Problem Using Proximal Policy Optimization with Curriculum Learning and Reward Engineering","created":"2024-04-03","cited_by_count":1,"area":"deeprl"},{"id":"2404.04106","title":"Intervention-Assisted Policy Gradient Methods for Online Stochastic Queuing Network Optimization: Technical Report","created":"2024-04-05","cited_by_count":1,"area":"deeprl"},{"id":"2405.19414","title":"Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning","created":"2024-05-29","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":"2501.16130","title":"ReFill: Reinforcement Learning for Fill-In Minimization","created":"2025-01-27","cited_by_count":1,"area":"deeprl"},{"id":"2502.18526","title":"Reinforcement Learning-based Approach for Vehicle-to-Building Charging with Heterogeneous Agents and Long Term Rewards","created":"2025-02-24","cited_by_count":1,"area":"deeprl"},{"id":"2503.12688","title":"Dynamic Angle Selection in X-Ray CT: A Reinforcement Learning Approach to Optimal Stopping","created":"2025-03-16","cited_by_count":1,"area":"deeprl"},{"id":"2503.16371","title":"Reinforcement Learning-based Heuristics to Guide Domain-Independent Dynamic Programming","created":"2025-03-20","cited_by_count":1,"area":"deeprl"},{"id":"2505.11136","title":"Reinforcement Learning for AMR Charging Decisions: The Impact of Reward and Action Space Design","created":"2025-05-16","cited_by_count":1,"area":"deeprl"},{"id":"2506.16352","title":"Data-Driven Policy Mapping for Safe RL-based Energy Management Systems","created":"2025-06-19","cited_by_count":1,"area":"deeprl"},{"id":"2507.16004","title":"Minor Embedding for Quantum Annealing with Reinforcement Learning","created":"2025-07-21","cited_by_count":1,"area":"deeprl"},{"id":"2511.00806","title":"Logic-informed reinforcement learning for cross-domain optimization of large-scale cyber-physical systems","created":"2025-11-02","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"},{"id":"2603.09090","title":"Overcoming Valid Action Suppression in Unmasked Policy Gradient Algorithms","created":"2026-03-10","cited_by_count":1,"area":"deeprl"},{"id":"2404.06423","title":"Deep Reinforcement Learning-Based Approach for a Single Vehicle Persistent Surveillance Problem with Fuel Constraints","created":"2024-04-09","cited_by_count":0,"area":"deeprl"},{"id":"2408.02022","title":"Scenario-based Thermal Management Parametrization Through Deep Reinforcement Learning","created":"2024-08-04","cited_by_count":0,"area":"deeprl"},{"id":"2409.10563","title":"Applying Action Masking and Curriculum Learning Techniques to Improve Data Efficiency and Overall Performance in Operational Technology Cyber Security using Reinforcement Learning","created":"2024-09-13","cited_by_count":0,"area":"deeprl"},{"id":"2501.14543","title":"Reducing Action Space for Deep Reinforcement Learning via Causal Effect Estimation","created":"2025-01-24","cited_by_count":0,"area":"deeprl"},{"id":"2502.12804","title":"Reinforcement Learning for Dynamic Resource Allocation in Optical Networks: Hype or Hope?","created":"2025-02-18","cited_by_count":0,"area":"deeprl"},{"id":"2506.02050","title":"Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids","created":"2025-06-01","cited_by_count":0,"area":"deeprl"},{"id":"2508.00641","title":"Reinforcement Learning for Decision-Level Interception Prioritization in Drone Swarm Defense","created":"2025-08-01","cited_by_count":0,"area":"deeprl"},{"id":"2508.14102","title":"Beyond Fixed Morphologies: Learning Graph Policies with Trust Region Compensation in Variable Action Spaces","created":"2025-08-16","cited_by_count":0,"area":"deeprl"},{"id":"2508.20102","title":"A Hierarchical Signal Coordination and Control System Using a Hybrid Model-based and Reinforcement Learning Approach","created":"2025-08-12","cited_by_count":0,"area":"deeprl"},{"id":"2509.01883","title":"Semi-on-Demand Transit Feeders with Shared Autonomous Vehicles and Reinforcement-Learning-Based Zonal Dispatching Control","created":"2025-09-02","cited_by_count":0,"area":"deeprl"},{"id":"2510.02589","title":"A Benchmark Study of Deep Reinforcement Learning Algorithms for the Container Stowage Planning Problem","created":"2025-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2511.03238","title":"Incorporating Quality of Life in Climate Adaptation Planning via Reinforcement Learning","created":"2025-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2512.13890","title":"Group-Theoretic Reinforcement Learning of Dynamical Decoupling Sequences","created":"2025-12-15","cited_by_count":0,"area":"deeprl"},{"id":"2512.19696","title":"QoS-Aware Dynamic CU Selection in O-RAN with Graph-Based Reinforcement Learning","created":"2025-11-21","cited_by_count":0,"area":"deeprl"},{"id":"2601.09293","title":"Policy-Based Reinforcement Learning with Action Masking for Dynamic Job Shop Scheduling under Uncertainty: Handling Random Arrivals and Machine Failures","created":"2026-01-14","cited_by_count":0,"area":"deeprl"},{"id":"2601.18586","title":"Learning long term climate-resilient transport adaptation pathways under direct and indirect flood impacts using reinforcement learning","created":"2026-01-26","cited_by_count":0,"area":"deeprl"},{"id":"2601.19452","title":"APC-RL: Exceeding Data-Driven Behavior Priors with Adaptive Policy Composition","created":"2026-01-27","cited_by_count":0,"area":"deeprl"},{"id":"2602.03968","title":"Safety-Critical Reinforcement Learning with Viability-Based Action Shielding for Hypersonic Longitudinal Flight","created":"2026-02-03","cited_by_count":0,"area":"deeprl"},{"id":"2602.06525","title":"Progress Constraints for Reinforcement Learning in Behavior Trees","created":"2026-02-06","cited_by_count":0,"area":"deeprl"},{"id":"2602.17685","title":"Optimal Multi-Debris Mission Planning in LEO: A Deep Reinforcement Learning Approach with Co-Elliptic Transfers and Refueling","created":"2026-02-04","cited_by_count":0,"area":"deeprl"},{"id":"2603.06278","title":"Artificial Intelligence for Climate Adaptation: Reinforcement Learning for Climate Change-Resilient Transport","created":"2026-03-06","cited_by_count":0,"area":"deeprl"},{"id":"2603.28385","title":"Critic-Free Deep Reinforcement Learning for Maritime Coverage Path Planning on Irregular Hexagonal Grids","created":"2026-03-30","cited_by_count":0,"area":"deeprl"},{"id":"2604.01886","title":"When does learning pay off? A study on DRL-based dynamic algorithm configuration for carbon-aware scheduling","created":"2026-04-02","cited_by_count":0,"area":"deeprl"},{"id":"2604.03768","title":"RL-Driven Sustainable Land-Use Allocation for the Lake Malawi Basin","created":"2026-04-04","cited_by_count":0,"area":"deeprl"},{"id":"2604.08685","title":"RAMP: Hybrid DRL for Online Learning of Numeric Action Models","created":"2026-04-09","cited_by_count":0,"area":"deeprl"},{"id":"2604.26566","title":"Learning to Route Electric Trucks Under Operational Uncertainty","created":"2026-04-29","cited_by_count":0,"area":"deeprl"},{"id":"2604.27266","title":"AutoREC: A reinforcement learning platform for equivalent circuit model generation","created":"2026-04-29","cited_by_count":0,"area":"deeprl"},{"id":"2605.15236","title":"Learning Selective Merge Policies for Deadline-Constrained Coded Caching via Deep Reinforcement Learning","created":"2026-05-13","cited_by_count":0,"area":"deeprl"},{"id":"2605.16312","title":"When Actions Disappear: Adversarial Action Removal in Self-Play Reinforcement Learning","created":"2026-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2605.16315","title":"A Structural Threshold in Decision Capacity Governs Collapse in Self-Play Reinforcement Learning","created":"2026-05-04","cited_by_count":0,"area":"deeprl"},{"id":"2605.23285","title":"Reinforcement Learning for Graph Generation under a Hard Assortativity Constraint","created":"2026-05-22","cited_by_count":0,"area":"deeprl"},{"id":"2605.31044","title":"The Challenges of Using Reinforcement Learning for Controlling Industrial Energy Systems","created":"2026-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2606.22159","title":"Deep RL for Fast Long-Horizon Operations Scheduling on NASA's Carruthers Geocorona Observatory Mission","created":"2026-06-20","cited_by_count":0,"area":"deeprl"},{"id":"2606.22922","title":"Hierarchical Reinforcement Learning for Sparse-Reward Search in Commutative Algebra","created":"2026-06-22","cited_by_count":0,"area":"deeprl"},{"id":"2607.23617","title":"Optimal Reward Shaping: Autonomous Car Parking Case Study","created":"2026-07-26","cited_by_count":0,"area":"deeprl"},{"id":"2608.20914","title":"Multi-Objective Deep Reinforcement Learning for Secure and Stable Power System Operation","created":"2026-08-21","cited_by_count":0,"area":"deeprl"},{"id":"2609.18441","title":"Multitask Reinforcement Learning for Assisting Choice Model Specification","created":"2026-09-16","cited_by_count":0,"area":"deeprl"},{"id":"2609.23590","title":"Cost-Aware Reinforcement Learning with Action Masking and Projection for Battery Energy Storage Dispatch under Suppressed-Spread Market Shifts","created":"2026-09-20","cited_by_count":0,"area":"deeprl"},{"id":"2609.28581","title":"Auditability Is Not One Property: Rule Overlap, Behavioural Agreement, and Composition in Reinforcement Learning","created":"2026-09-23","cited_by_count":0,"area":"deeprl"},{"id":"2609.34265","title":"ZeroCode: On-demand Error-Correcting Code Construction from the Zero Matrix via Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"deeprl"},{"id":"2610.16921","title":"Time Window Optimization for Motor Imagery Classification via Temporal Structure Embedded Reinforcement Learning","created":"2026-10-12","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}