{"total":60,"rows":[{"id":"2306.17100","title":"RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","created":"2023-06-29","cited_by_count":71,"area":null},{"id":"2310.12934","title":"Generative Flow Networks as Entropy-Regularized RL","created":"2023-10-19","cited_by_count":64,"area":null},{"id":"2510.12633","title":"Laminar: A Scalable Asynchronous RL Post-Training Framework","created":"2025-10-14","cited_by_count":37,"area":null},{"id":"2309.12825","title":"OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control","created":"2023-09-22","cited_by_count":33,"area":null},{"id":"2312.01472","title":"BenchMARL: Benchmarking Multi-Agent Reinforcement Learning","created":"2023-12-03","cited_by_count":33,"area":null},{"id":"2405.00662","title":"No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO","created":"2024-05-01","cited_by_count":27,"area":"deeprl"},{"id":"2502.02133","title":"Synthesis of Model Predictive Control and Reinforcement Learning: Survey and Classification","created":"2025-02-04","cited_by_count":26,"area":"deeprl"},{"id":"2510.01051","title":"GEM: A Gym for Agentic LLMs","created":"2025-10-01","cited_by_count":23,"area":"agents"},{"id":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17,"area":"deeprl"},{"id":"2405.04657","title":"ACEGEN: Reinforcement learning of generative chemical agents for drug discovery","created":"2024-05-07","cited_by_count":14,"area":"deeprl"},{"id":"2405.15054","title":"Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning","created":"2024-05-23","cited_by_count":11,"area":null},{"id":"2408.00170","title":"CREW: Facilitating Human-AI Teaming Research","created":"2024-07-31","cited_by_count":11,"area":null},{"id":"2306.11551","title":"IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2312.03814","title":"Pearl: A Production-ready Reinforcement Learning Agent","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2508.14734","title":"AFABench: A Generic Framework for Benchmarking Active Feature Acquisition","created":"2025-08-20","cited_by_count":9,"area":"deeprl"},{"id":"2508.00234","title":"Quality-of-Service Aware LLM Routing for Edge Computing with Multiple Experts","created":"2025-08-01","cited_by_count":7,"area":null},{"id":"2311.18736","title":"Controlgym: Large-Scale Control Environments for Benchmarking Reinforcement Learning Algorithms","created":"2023-11-30","cited_by_count":6,"area":null},{"id":"2506.01541","title":"Adaptive Destruction Processes for Diffusion Samplers","created":"2025-06-02","cited_by_count":6,"area":"diffusion"},{"id":"2503.01919","title":"Reinforcement learning with combinatorial actions for coupled restless bandits","created":"2025-03-01","cited_by_count":5,"area":"deeprl"},{"id":"2306.03530","title":"RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control","created":"2023-06-06","cited_by_count":4,"area":null},{"id":"2407.16807","title":"In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning","created":"2024-07-23","cited_by_count":4,"area":"deeprl"},{"id":"2412.16244","title":"The impact of behavioral diversity in multi-agent reinforcement learning","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2505.17734","title":"URB -- Urban Routing Benchmark for RL-equipped Connected Autonomous Vehicles","created":"2025-05-23","cited_by_count":4,"area":"driving"},{"id":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"id":"2410.04988","title":"Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling","created":"2024-10-07","cited_by_count":3,"area":"deeprl"},{"id":"2502.20065","title":"RouteRL: Multi-agent reinforcement learning framework for urban route choice with autonomous vehicles","created":"2025-02-27","cited_by_count":3,"area":"driving"},{"id":"2604.23841","title":"Scalable Production Scheduling: Linear Complexity via Unified Homogeneous Graphs","created":"2026-04-26","cited_by_count":3,"area":null},{"id":"2506.09434","title":"When Is Diversity Rewarded in Cooperative Multi-Agent Learning?","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2506.20554","title":"Reinforcement Learning Increases Wind Farm Power Production by Enabling Closed-Loop Collaborative Control","created":"2025-06-25","cited_by_count":2,"area":"deeprl"},{"id":"2601.15015","title":"Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control","created":"2026-01-21","cited_by_count":2,"area":"deeprl"},{"id":"2606.08729","title":"IR-SIM: A Lightweight Declarative Simulator for Navigation Learning and Benchmarking","created":"2026-06-07","cited_by_count":2,"area":null},{"id":"2405.03262","title":"End-to-End Reinforcement Learning of Curative Curtailment with Partial Measurement Availability","created":"2024-05-06","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":"2506.04265","title":"Cooperative Game-Theoretic Credit Assignment for Multi-Agent Policy Gradients via the Core","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2511.03100","title":"Scaling Multi-Agent Environment Co-Design with Diffusion Models","created":"2025-11-05","cited_by_count":1,"area":"diffusion"},{"id":"2601.22211","title":"Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions","created":"2026-01-29","cited_by_count":1,"area":"deeprl"},{"id":"2608.23297","title":"ADDA: a Modular Framework for Representing, Simulating and Assimilating Dynamics with End-to-end Differentiability","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2402.04211","title":"Probabilistic Shapley Value Modeling and Inference","created":"2024-02-06","cited_by_count":0,"area":null},{"id":"2406.17490","title":"BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO","created":"2024-06-25","cited_by_count":0,"area":"deeprl"},{"id":"2408.04531","title":"AExGym: Benchmarks and Environments for Adaptive Experimentation","created":"2024-08-08","cited_by_count":0,"area":null},{"id":"2408.06503","title":"Enhancing Heterogeneous Multi-Agent Cooperation in Decentralized MARL via GNN-driven Intrinsic Rewards","created":"2024-08-12","cited_by_count":0,"area":null},{"id":"2410.12598","title":"Dynamic Learning Rate for Deep Reinforcement Learning: A Bandit Approach","created":"2024-10-16","cited_by_count":0,"area":"deeprl"},{"id":"2411.14411","title":"Multi-Agent Environments for Vehicle Routing Problems","created":"2024-11-21","cited_by_count":0,"area":null},{"id":"2412.20946","title":"Generalising Battery Control in Net-Zero Buildings via Personalised Federated RL","created":"2024-12-30","cited_by_count":0,"area":null},{"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":"2507.03487","title":"ObjectRL: An Object-Oriented Reinforcement Learning Codebase","created":"2025-07-04","cited_by_count":0,"area":"deeprl"},{"id":"2508.09325","title":"SegDAC: Visual Generalization in Reinforcement Learning via Dynamic Object Tokens","created":"2025-08-12","cited_by_count":0,"area":"deeprl"},{"id":"2509.25475","title":"TDHook: A Lightweight Framework for Interpretability","created":"2025-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2510.08763","title":"Reinforcement Learning-Based Optimization of CT Acquisition and Reconstruction Parameters Through Virtual Imaging Trials","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2511.16158","title":"MagBotSim: Physics-Based Simulation and Reinforcement Learning Environments for Magnetic Robotics","created":"2025-11-20","cited_by_count":0,"area":"deeprl"},{"id":"2602.01915","title":"VLM-Guided Experience Replay","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2602.11437","title":"Distributionally Robust Cooperative Multi-Agent Reinforcement Learning via Robust Value Factorization","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.01260","title":"MOSAIC: A Universal Agent-Level Interface for Cross-Paradigm Agent Mixing and Human-AI Collaboration","created":"2026-03-01","cited_by_count":0,"area":"agents"},{"id":"2603.04659","title":"GIANT - Global Path Integration and Attentive Graph Networks for Multi-Agent Trajectory Planning","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2605.21442","title":"torchtune: PyTorch native post-training library","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.02027","title":"World-Task Factorization for Robot Learning","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.16004","title":"Robustness of Reinforcement Learning-Based Congestion Management in Low-Voltage Grids","created":"2026-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2607.26336","title":"Learning Implicit Causal World Models from Multi-Agent Demonstrations","created":"2026-07-28","cited_by_count":0,"area":"wm"},{"id":"2609.13309","title":"Task-Based CT Protocol Optimization Using Reinforcement Learning and Virtual Imaging Trials","created":"2026-09-10","cited_by_count":0,"area":"deeprl"},{"id":"2610.18808","title":"Optimizing Team Behavior via Extremum-seeking Control in Multi-agent Reinforcement Learning","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}