{"total":8,"rows":[{"id":"2102.03718","title":"An Analysis of Frame-skipping in Reinforcement Learning","created":"2021-02-07","cited_by_count":18,"area":null},{"id":"2106.12729","title":"Finite-Sample Analysis of Off-Policy TD-Learning via Generalized Bellman Operators","created":"2021-06-24","cited_by_count":17,"area":null},{"id":"2310.13129","title":"Deep Reinforcement Learning-based Intelligent Traffic Signal Controls with Optimized CO2 emissions","created":"2023-10-19","cited_by_count":2,"area":null},{"id":"2402.01802","title":"An Auction-based Marketplace for Model Trading in Federated Learning","created":"2024-02-02","cited_by_count":2,"area":null},{"id":"2102.09824","title":"Sim-Env: Decoupling OpenAI Gym Environments from Simulation Models","created":"2021-02-19","cited_by_count":1,"area":null},{"id":"2302.13877","title":"DeepADMR: A Deep Learning based Anomaly Detection for MANET Routing","created":"2023-01-24","cited_by_count":1,"area":null},{"id":"2401.07044","title":"BP(\\lambda): Online Learning via Synthetic Gradients","created":"2024-01-13","cited_by_count":0,"area":null},{"id":"2507.19539","title":"Swift-Sarsa: Fast and Robust Linear Control","created":"2025-07-22","cited_by_count":0,"area":null}],"next_cursor":null}