{"total":19,"rows":[{"id":"2404.14238","title":"Beyond the Edge: An Advanced Exploration of Reinforcement Learning for Mobile Edge Computing, its Applications, and Future Research Trajectories","created":"2024-04-22","cited_by_count":9,"area":"deeprl"},{"id":"2501.13448","title":"BMG-Q: Localized Bipartite Match Graph Attention Q-Learning for Ride-Pooling Order Dispatch","created":"2025-01-23","cited_by_count":7,"area":"deeprl"},{"id":"2412.17707","title":"SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC","created":"2024-12-23","cited_by_count":5,"area":"deeprl"},{"id":"2503.14555","title":"A Generalist Hanabi Agent","created":"2025-03-17","cited_by_count":5,"area":"deeprl"},{"id":"2403.08906","title":"Strategizing against Q-learners: A Control-theoretical Approach","created":"2024-03-13","cited_by_count":2,"area":"deeprl"},{"id":"2404.03710","title":"Self-organized free-flight arrival for urban air mobility","created":"2024-04-04","cited_by_count":2,"area":"deeprl"},{"id":"2411.16519","title":"Reinforcement Learning for Bidding Strategy Optimization in Day-Ahead Energy Market","created":"2024-11-25","cited_by_count":2,"area":"deeprl"},{"id":"2505.24155","title":"Biological Pathway Guided Gene Selection Through Collaborative Reinforcement Learning","created":"2025-05-30","cited_by_count":2,"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":"2405.02044","title":"Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach","created":"2024-05-03","cited_by_count":0,"area":"deeprl"},{"id":"2406.05041","title":"Online Frequency Scheduling by Learning Parallel Actions","created":"2024-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2412.12605","title":"An Advantage-based Optimization Method for Reinforcement Learning in Large Action Space","created":"2024-12-17","cited_by_count":0,"area":"deeprl"},{"id":"2505.22979","title":"Learning Recommender Mechanisms for Bayesian Stochastic Games","created":"2025-05-29","cited_by_count":0,"area":"deeprl"},{"id":"2511.18000","title":"Reward Engineering for Spatial Epidemic Simulations: A Reinforcement Learning Platform for Individual Behavioral Learning","created":"2025-11-22","cited_by_count":0,"area":"deeprl"},{"id":"2602.11735","title":"AC-MASAC: An Attentive Curriculum Learning Framework for Heterogeneous UAV Swarm Coordination","created":"2026-02-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.15528","title":"Task-Semantic Graph-Driven Distributed Agent Networking for Underwater Target Tracking","created":"2026-05-15","cited_by_count":0,"area":"deeprl"},{"id":"2606.12281","title":"CCKS: Consensus-based Communication and Knowledge Sharing","created":"2026-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2606.30092","title":"Hierarchical Reinforcement Learning in StarCraft Micromanagement with Influence Maps and Cluster-based Scripts","created":"2026-06-29","cited_by_count":0,"area":"deeprl"},{"id":"2607.16177","title":"Physics-enhanced reinforcement learning for real-time optimal control of dynamical systems","created":"2026-07-17","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}