{"total":26,"rows":[{"id":"2405.17743","title":"ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling","created":"2024-05-28","cited_by_count":124,"area":null},{"id":"2305.18901","title":"Policy Optimization for Continuous Reinforcement Learning","created":"2023-05-30","cited_by_count":31,"area":null},{"id":"2207.06272","title":"Hindsight Learning for MDPs with Exogenous Inputs","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2106.03442","title":"Average-Reward Reinforcement Learning with Trust Region Methods","created":"2021-06-07","cited_by_count":19,"area":null},{"id":"2305.16483","title":"Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks","created":"2023-05-25","cited_by_count":9,"area":null},{"id":"2105.08769","title":"Learning and Information in Stochastic Networks and Queues","created":"2021-05-18","cited_by_count":8,"area":null},{"id":"2205.11168","title":"Logarithmic regret bounds for continuous-time average-reward Markov decision processes","created":"2022-05-23","cited_by_count":8,"area":null},{"id":"2211.07092","title":"Offline Estimation of Controlled Markov Chains: Minimaxity and Sample Complexity","created":"2022-11-14","cited_by_count":5,"area":null},{"id":"2101.07312","title":"Benchmarking Perturbation-based Saliency Maps for Explaining Atari Agents","created":"2021-01-18","cited_by_count":4,"area":null},{"id":"2212.06338","title":"Minimax Optimal Estimation of Stability Under Distribution Shift","created":"2022-12-13","cited_by_count":4,"area":null},{"id":"2107.08068","title":"Refined Policy Improvement Bounds for MDPs","created":"2021-07-16","cited_by_count":3,"area":null},{"id":"2303.03399","title":"Online Learning and Optimization for Queues with Unknown Demand Curve and Service Distribution","created":"2023-03-06","cited_by_count":3,"area":null},{"id":"2410.06170","title":"QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2306.02574","title":"Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space","created":"2023-06-05","cited_by_count":2,"area":null},{"id":"2507.12642","title":"QSpark: Towards Reliable Qiskit Code Generation","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2206.10073","title":"Finding Optimal Policy for Queueing Models: New Parameterization","created":"2022-06-21","cited_by_count":1,"area":null},{"id":"2307.12405","title":"Optimal Control of Multiclass Fluid Queueing Networks: A Machine Learning Approach","created":"2023-07-23","cited_by_count":1,"area":null},{"id":"2408.16215","title":"Adversarial Network Optimization under Bandit Feedback: Maximizing Utility in Non-Stationary Multi-Hop Networks","created":"2024-08-29","cited_by_count":1,"area":null},{"id":"2202.01729","title":"Can machines solve general queueing systems?","created":"2022-02-03","cited_by_count":0,"area":null},{"id":"2306.01896","title":"Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2503.14927","title":"Semi-Gradient SARSA Routing with Theoretical Guarantee on Traffic Stability and Weight Convergence","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2506.20543","title":"Demonstration of effective UCB-based routing in skill-based queues on real-world data","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2510.14097","title":"Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2601.20694","title":"Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2606.11487","title":"Unbiased Derivative Estimation for Stationary Mean of Parameterized Markov chains","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2609.06881","title":"Learning Adaptive SED for heterogeneous load balancing","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}