{"total":8,"rows":[{"id":"2404.14367","title":"Preference Fine-Tuning of LLMs Should Leverage Suboptimal, On-Policy Data","created":"2024-04-22","cited_by_count":185,"area":null},{"id":"2402.17235","title":"Stochastic Gradient Succeeds for Bandits","created":"2024-02-27","cited_by_count":10,"area":null},{"id":"2310.11897","title":"Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning","created":"2023-10-18","cited_by_count":4,"area":null},{"id":"2502.07141","title":"Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2307.11957","title":"High-performance real-world optical computing trained by in situ gradient-based model-free optimization","created":"2023-07-22","cited_by_count":1,"area":null},{"id":"2603.15001","title":"How Log-Barrier Helps Exploration in Policy Optimization","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2306.10587","title":"Acceleration in Policy Optimization","created":"2023-06-18","cited_by_count":0,"area":null},{"id":"2604.22140","title":"Concave Statistical Utility Maximization Bandits via Influence-Function Gradients","created":"2026-04-24","cited_by_count":0,"area":null}],"next_cursor":null}