{"total":83,"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":"2307.06125","title":"Learning Hierarchical Interactive Multi-Object Search for Mobile Manipulation","created":"2023-07-12","cited_by_count":14,"area":null},{"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":"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":"2304.09970","title":"Learning policies for resource allocation in business processes","created":"2023-04-19","cited_by_count":4,"area":null},{"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":"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":"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":"2509.25850","title":"RL-Guided Data Selection for Language Model Finetuning","created":"2025-09-30","cited_by_count":2,"area":null},{"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":"2404.01308","title":"Learning to Solve Job Shop Scheduling under Uncertainty","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2505.19315","title":"Demand Selection for VRP with Emission Quota","created":"2025-05-25","cited_by_count":1,"area":null},{"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":"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":"2404.13061","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":"2408.15041","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":"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":"2505.01966","title":"A Goal-Oriented Reinforcement Learning-Based Path Planning Algorithm for Modular Self-Reconfigurable Satellites","created":"2025-05-04","cited_by_count":0,"area":null},{"id":"2506.08893","title":"Real-Time Cascade Mitigation in Power Systems Using Influence Graph Improved by Reinforcement Learning","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2507.15574","title":"On the Role of AI in Managing Satellite Constellations: Insights from the ConstellAI Project","created":"2025-07-21","cited_by_count":0,"area":null},{"id":"2507.16635","title":"Novel Multi-Agent Action Masked Deep Reinforcement Learning for General Industrial Assembly Lines Balancing Problems","created":"2025-07-22","cited_by_count":0,"area":null},{"id":"2509.10499","title":"Towards Scalable O-RAN Resource Management: Graph-Augmented Proximal Policy Optimization","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2509.23905","title":"Integrated Communication and Control for Energy-Efficient UAV Swarms: A Multi-Agent Reinforcement Learning Approach","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2510.01094","title":"Optimizing Fairness in Production Planning: A Human-Centric Approach to Machine and Workforce Allocation","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2510.24113","title":"Taming the Tail: NoI Topology Synthesis for Mixed DL Workloads on Chiplet-Based Accelerators","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2511.03243","title":"Climate Adaptation with Reinforcement Learning: Economic vs. Quality of Life Adaptation Pathways","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2511.13214","title":"Learning to Solve Resource-Constrained Project Scheduling Problems with Duration Uncertainty using Graph Neural Networks","created":"2025-11-17","cited_by_count":0,"area":null},{"id":"2512.17444","title":"Assessing Long-Term Electricity Market Design for Ambitious Decarbonization Targets using Multi-Agent Reinforcement Learning","created":"2025-12-19","cited_by_count":0,"area":null},{"id":"2512.19767","title":"Learning to Design City-scale Transit Routes","created":"2025-12-21","cited_by_count":0,"area":null},{"id":"2602.00014","title":"What Artificial Intelligence can do for High-Performance Computing systems?","created":"2026-01-03","cited_by_count":0,"area":null},{"id":"2602.00035","title":"Asynchronous MultiAgent Reinforcement Learning for 5G Routing under Side Constraints","created":"2026-01-18","cited_by_count":0,"area":null},{"id":"2603.06608","title":"Two-Bridge: Exclusive Objectives and Extended Horizon StarCraft II Benchmark","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.19864","title":"NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2605.05795","title":"Reward Shaping and Action Masking for Compositional Tasks using Behavior Trees and LLMs","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.13570","title":"Learning Local Constraints for Reinforcement-Learned Content Generators","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.28730","title":"AlphaTransit: Learning to Design City-scale Transit Routes","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.10979","title":"Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.16330","title":"Phase-Aware Guidance Injection for Recurrent MAPPO in Assembly-Line Disruption Recovery","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.12363","title":"EU-ETS under attack? The impact of carbon price suppression on the decarbonization of the power sector","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.28499","title":"REPLICANT: Learning Policies for Evading and Hardening Malware Detectors","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2610.03454","title":"Measure Less, Know More: Self-Supervised Test-Time Feature Acquisition","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.07638","title":"Learning Explainable Representations of Complex Game-playing Strategies","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.13923","title":"Goal-Oriented Bundle Management and Flow Control for Deep-Space Communications via Reinforcement Learning","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}