{"total":16,"rows":[{"id":"2210.06718","title":"Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient","created":"2022-10-13","cited_by_count":161,"area":null},{"id":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27,"area":null},{"id":"2310.16173","title":"On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\\epsilon$-Greedy Exploration","created":"2023-10-24","cited_by_count":17,"area":null},{"id":"2405.19883","title":"From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems","created":"2024-05-30","cited_by_count":17,"area":null},{"id":"2209.07376","title":"Understanding Deep Neural Function Approximation in Reinforcement Learning via $\\epsilon$-Greedy Exploration","created":"2022-09-15","cited_by_count":11,"area":null},{"id":"2302.09703","title":"Reinforcement Learning with Function Approximation: From Linear to Nonlinear","created":"2023-02-20","cited_by_count":4,"area":null},{"id":"2312.08369","title":"The Effective Horizon Explains Deep RL Performance in Stochastic Environments","created":"2023-12-13","cited_by_count":3,"area":null},{"id":"2408.04251","title":"Cooperative Multi-Agent Deep Reinforcement Learning in Content Ranking Optimization","created":"2024-08-08","cited_by_count":2,"area":null},{"id":"2309.11984","title":"State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2409.13671","title":"A Generative Framework for Predictive Modeling of Multiple Chronic Conditions Using Graph Variational Autoencoder and Bandit-Optimized Graph Neural Network","created":"2024-09-20","cited_by_count":1,"area":null},{"id":"2506.20607","title":"H-FEX: A Symbolic Learning Method for Hamiltonian Systems","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2306.17329","title":"Kernel $\\epsilon$-Greedy for Multi-Armed Bandits with Covariates","created":"2023-06-29","cited_by_count":0,"area":null},{"id":"2312.12781","title":"DynaLay: An Introspective Approach to Dynamic Layer Selection for Deep Networks","created":"2023-12-20","cited_by_count":0,"area":null},{"id":"2501.00562","title":"An Overview and Discussion on Using Large Language Models for Implementation Generation of Solutions to Open-Ended Problems","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2505.16918","title":"Scalable and Interpretable Contextual Bandits: A Literature Review and Retail Offer Prototype","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2510.08469","title":"Platform-Agnostic Modular Architecture for Quantum Benchmarking","created":"2025-10-09","cited_by_count":0,"area":null}],"next_cursor":null}