{"total":23,"rows":[{"id":"2104.07886","title":"Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks","created":"2021-04-16","cited_by_count":38,"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":"2303.02160","title":"Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2201.05000","title":"Automated Reinforcement Learning: An Overview","created":"2022-01-13","cited_by_count":9,"area":null},{"id":"2312.02405","title":"BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks","created":"2023-12-05","cited_by_count":8,"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":"2107.00703","title":"Distilling Reinforcement Learning Tricks for Video Games","created":"2021-07-01","cited_by_count":3,"area":null},{"id":"2208.04537","title":"Automating DBSCAN via Deep Reinforcement Learning","created":"2022-08-09","cited_by_count":3,"area":null},{"id":"2308.08500","title":"InTune: Reinforcement Learning-based Data Pipeline Optimization for Deep Recommendation Models","created":"2023-08-13","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":"2203.00636","title":"Distributional Reinforcement Learning for Scheduling of Chemical Production Processes","created":"2022-03-01","cited_by_count":2,"area":null},{"id":"2204.07543","title":"CryoRL: Reinforcement Learning Enables Efficient Cryo-EM Data Collection","created":"2022-04-15","cited_by_count":1,"area":null},{"id":"2206.12700","title":"Towards Modern Card Games with Large-Scale Action Spaces Through Action Representation","created":"2022-06-25","cited_by_count":1,"area":null},{"id":"2309.01825","title":"LoopTune: Optimizing Tensor Computations with Reinforcement Learning","created":"2023-09-04","cited_by_count":1,"area":null},{"id":"2505.04339","title":"Adaptive and Robust DBSCAN with Multi-agent Reinforcement Learning","created":"2025-05-07","cited_by_count":1,"area":null},{"id":"2108.09478","title":"MimicBot: Combining Imitation and Reinforcement Learning to win in Bot Bowl","created":"2021-08-21","cited_by_count":0,"area":null},{"id":"2308.14521","title":"Context-Aware Composition of Agent Policies by Markov Decision Process Entity Embeddings and Agent Ensembles","created":"2023-08-28","cited_by_count":0,"area":null},{"id":"2504.05633","title":"To Start Up a Start-Up$-$Embedding Strategic Demand Development in Operational On-Demand Fulfillment via Reinforcement Learning with Information Shaping","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2603.02846","title":"Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling","created":"2026-03-03","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":"2605.30622","title":"Jamming-Resilient PRB Reservation for Latency-Critical O-RAN Network Slicing","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2609.32752","title":"Action Shaping: Policies Absorb What They Can Express","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}