{"total":171,"rows":[{"id":"2210.01241","title":"Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization","created":"2022-10-03","cited_by_count":246,"area":null},{"id":"2306.12964","title":"Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning","created":"2023-05-25","cited_by_count":39,"area":null},{"id":"2104.01678","title":"Understanding Continual Learning Settings with Data Distribution Drift Analysis","created":"2021-04-04","cited_by_count":38,"area":null},{"id":"2205.06750","title":"Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking","created":"2022-05-13","cited_by_count":34,"area":null},{"id":"2212.11498","title":"Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers","created":"2022-12-22","cited_by_count":30,"area":null},{"id":"2406.18394","title":"AlphaForge: A Framework to Mine and Dynamically Combine Formulaic Alpha Factors","created":"2024-06-26","cited_by_count":27,"area":null},{"id":"2210.10691","title":"Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes","created":"2022-10-19","cited_by_count":26,"area":null},{"id":"2211.15557","title":"Beyond CAGE: Investigating Generalization of Learned Autonomous Network Defense Policies","created":"2022-11-28","cited_by_count":23,"area":null},{"id":"2104.03760","title":"A Reinforcement Learning Environment For Job-Shop Scheduling","created":"2021-04-08","cited_by_count":21,"area":null},{"id":"2105.13807","title":"Gym-$\\mu$RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning","created":"2021-05-21","cited_by_count":19,"area":null},{"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":"2307.06125","title":"Learning Hierarchical Interactive Multi-Object Search for Mobile Manipulation","created":"2023-07-12","cited_by_count":14,"area":null},{"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":"2311.15341","title":"Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning","created":"2023-11-26","cited_by_count":10,"area":null},{"id":"2104.07294","title":"Generalising Discrete Action Spaces with Conditional Action Trees","created":"2021-04-15","cited_by_count":6,"area":null},{"id":"2206.10122","title":"Safe and Psychologically Pleasant Traffic Signal Control with Reinforcement Learning using Action Masking","created":"2022-06-21","cited_by_count":6,"area":null},{"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":"2104.00527","title":"Deep Reinforcement Learning for Constrained Field Development Optimization in Subsurface Two-phase Flow","created":"2021-03-31","cited_by_count":5,"area":null},{"id":"2211.15068","title":"Learning to design without prior data: Discovering generalizable design strategies using deep learning and tree search","created":"2022-11-28","cited_by_count":5,"area":null},{"id":"2305.06378","title":"Discovery of Optimal Quantum Error Correcting Codes via Reinforcement Learning","created":"2023-05-10","cited_by_count":5,"area":null},{"id":"2408.10162","title":"Physics-Aware Combinatorial Assembly Sequence Planning using Data-free Action Masking","created":"2024-08-19","cited_by_count":5,"area":null},{"id":"2411.15212","title":"Effective Analog ICs Floorplanning with Relational Graph Neural Networks and Reinforcement Learning","created":"2024-11-20","cited_by_count":5,"area":null},{"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":"2304.09970","title":"Learning policies for resource allocation in business processes","created":"2023-04-19","cited_by_count":4,"area":null},{"id":"2508.13070","title":"Reinforced Context Order Recovery for Adaptive Reasoning and Planning","created":"2025-08-18","cited_by_count":4,"area":"lr"},{"id":"2111.08819","title":"CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms","created":"2021-11-16","cited_by_count":3,"area":null},{"id":"2309.03157","title":"Learning to Recharge: UAV Coverage Path Planning through Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":3,"area":null},{"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":"2410.21151","title":"BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces","created":"2024-10-28","cited_by_count":3,"area":"offlinerl"},{"id":"2508.16581","title":"Increasing Interaction Fidelity: Training Routines for Biomechanical Models in HCI","created":"2025-08-05","cited_by_count":3,"area":null},{"id":"2510.16097","title":"Narrowing Action Choices with AI Improves Human Sequential Decisions","created":"2025-10-17","cited_by_count":3,"area":null},{"id":"2105.08666","title":"Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2202.04367","title":"A Reinforcement Learning Approach to Domain-Knowledge Inclusion Using Grammar Guided Symbolic Regression","created":"2022-02-09","cited_by_count":2,"area":null},{"id":"2301.11461","title":"Learning to Generate All Feasible Actions","created":"2023-01-26","cited_by_count":2,"area":null},{"id":"2303.16737","title":"Multi-Agent Reinforcement Learning with Action Masking for UAV-enabled Mobile Communications","created":"2023-03-29","cited_by_count":2,"area":null},{"id":"2304.14698","title":"X-RLflow: Graph Reinforcement Learning for Neural Network Subgraphs Transformation","created":"2023-04-28","cited_by_count":2,"area":null},{"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":"2410.02253","title":"From Imitation to Exploration: End-to-end Autonomous Driving based on World Model","created":"2024-10-03","cited_by_count":2,"area":"wm"},{"id":"2410.09134","title":"Multi-Agent Actor-Critics in Autonomous Cyber Defense","created":"2024-10-11","cited_by_count":2,"area":null},{"id":"2411.19359","title":"Integrating Transit Signal Priority into Multi-Agent Reinforcement Learning based Traffic Signal Control","created":"2024-11-28","cited_by_count":2,"area":null},{"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":"2509.25850","title":"RL-Guided Data Selection for Language Model Finetuning","created":"2025-09-30","cited_by_count":2,"area":null},{"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":"2606.00708","title":"MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition","created":"2026-05-30","cited_by_count":2,"area":"agents"},{"id":"2207.10376","title":"Multi-Asset Closed-Loop Reservoir Management Using Deep Reinforcement Learning","created":"2022-07-21","cited_by_count":1,"area":null},{"id":"2301.03679","title":"Transformers as Policies for Variable Action Environments","created":"2023-01-09","cited_by_count":1,"area":null},{"id":"2301.06870","title":"Learning to solve arithmetic problems with a virtual abacus","created":"2023-01-17","cited_by_count":1,"area":null},{"id":"2305.13824","title":"Constrained Reinforcement Learning for Dynamic Material Handling","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2307.11704","title":"JoinGym: An Efficient Query Optimization Environment for Reinforcement Learning","created":"2023-07-21","cited_by_count":1,"area":null},{"id":"2308.11621","title":"Reinforcement Learning -based Adaptation and Scheduling Methods for Multi-source DASH","created":"2023-07-25","cited_by_count":1,"area":null},{"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":"2404.01308","title":"Learning to Solve Job Shop Scheduling under Uncertainty","created":"2024-03-04","cited_by_count":1,"area":null},{"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":"2502.13006","title":"Integrating Reinforcement Learning, Action Model Learning, and Numeric Planning for Tackling Complex Tasks","created":"2025-02-18","cited_by_count":1,"area":"offlinerl"},{"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":"2505.19315","title":"Demand Selection for VRP with Emission Quota","created":"2025-05-25","cited_by_count":1,"area":null},{"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":"2507.05251","title":"Action Space Reduction Strategies for Reinforcement Learning in Autonomous Driving","created":"2025-07-07","cited_by_count":1,"area":"driving"},{"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":"2511.02314","title":"Large-scale automatic carbon ion treatment planning for head and neck cancers via parallel multi-agent reinforcement learning","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2602.03195","title":"Reinforcement Learning with Promising Tokens for Large Language Models","created":"2026-02-03","cited_by_count":1,"area":null},{"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":"2605.06066","title":"Causal Reinforcement Learning for Complex Card Games: A Magic The Gathering Benchmark","created":"2026-05-07","cited_by_count":1,"area":"wm"},{"id":"2110.09035","title":"Edge Rewiring Goes Neural: Boosting Network Resilience without Rich Features","created":"2021-10-18","cited_by_count":0,"area":null},{"id":"2205.13675","title":"Reinforcement Learning Approach for Mapping Applications to Dataflow-Based Coarse-Grained Reconfigurable Array","created":"2022-05-26","cited_by_count":0,"area":null},{"id":"2211.15589","title":"Inapplicable Actions Learning for Knowledge Transfer in Reinforcement Learning","created":"2022-11-28","cited_by_count":0,"area":null},{"id":"2302.03517","title":"Optimization of Topology-Aware Job Allocation on a High-Performance Computing Cluster by Neural Simulated Annealing","created":"2023-02-06","cited_by_count":0,"area":null},{"id":"2304.13004","title":"Centralized control for multi-agent RL in a complex Real-Time-Strategy game","created":"2023-04-25","cited_by_count":0,"area":null},{"id":"2305.10760","title":"Automatic Design Method of Building Pipeline Layout Based on Deep Reinforcement Learning","created":"2023-05-18","cited_by_count":0,"area":null},{"id":"2306.14178","title":"A Framework for dynamically meeting performance objectives on a service mesh","created":"2023-06-25","cited_by_count":0,"area":null},{"id":"2310.12359","title":"MARVEL: Multi-Agent Reinforcement-Learning for Large-Scale Variable Speed Limits","created":"2023-10-18","cited_by_count":0,"area":null},{"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":"2404.13061","title":"FPGA Divide-and-Conquer Placement using Deep Reinforcement Learning","created":"2024-04-11","cited_by_count":0,"area":null},{"id":"2406.08766","title":"Injecting Combinatorial Optimization into MCTS: Application to the Board Game boop","created":"2024-06-13","cited_by_count":0,"area":null},{"id":"2408.02022","title":"Scenario-based Thermal Management Parametrization Through Deep Reinforcement Learning","created":"2024-08-04","cited_by_count":0,"area":"deeprl"},{"id":"2408.15041","title":"Earth Observation Satellite Scheduling with Graph Neural Networks and Monte Carlo Tree Search","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2409.00107","title":"Evaluating the Impact of Multiple DER Aggregators on Wholesale Energy Markets: A Hybrid Mean Field Approach","created":"2024-08-27","cited_by_count":0,"area":null},{"id":"2409.00754","title":"Cooperative Path Planning with Asynchronous Multiagent Reinforcement Learning","created":"2024-09-01","cited_by_count":0,"area":null},{"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":"2410.06372","title":"Cooperative and Asynchronous Transformer-based Mission Planning for Heterogeneous Teams of Mobile Robots","created":"2024-10-08","cited_by_count":0,"area":null},{"id":"2411.07634","title":"Exploring Multi-Agent Reinforcement Learning for Unrelated Parallel Machine Scheduling","created":"2024-11-12","cited_by_count":0,"area":null},{"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"}],"next_cursor":"100"}