{"total":25,"rows":[{"id":"2103.12158","title":"Convergence of Finite Memory Q-Learning for POMDPs and Near Optimality of Learned Policies under Filter Stability","created":"2021-03-22","cited_by_count":22,"area":null},{"id":"2111.00289","title":"Intrusion Prevention through Optimal Stopping","created":"2021-10-30","cited_by_count":18,"area":null},{"id":"2301.06085","title":"Learning Near-Optimal Intrusion Responses Against Dynamic Attackers","created":"2023-01-11","cited_by_count":15,"area":null},{"id":"2402.12499","title":"Automated Security Response through Online Learning with Adaptive Conjectures","created":"2024-02-19","cited_by_count":13,"area":null},{"id":"2407.11070","title":"Optimal Defender Strategies for CAGE-2 using Causal Modeling and Tree Search","created":"2024-07-12","cited_by_count":12,"area":null},{"id":"2106.07160","title":"Learning Intrusion Prevention Policies through Optimal Stopping","created":"2021-06-14","cited_by_count":11,"area":null},{"id":"2309.03292","title":"Scalable Learning of Intrusion Responses through Recursive Decomposition","created":"2023-09-06","cited_by_count":8,"area":null},{"id":"2404.01741","title":"Intrusion Tolerance for Networked Systems through Two-Level Feedback Control","created":"2024-04-02","cited_by_count":8,"area":null},{"id":"2205.14694","title":"Learning Security Strategies through Game Play and Optimal Stopping","created":"2022-05-29","cited_by_count":5,"area":null},{"id":"2508.14385","title":"Online Incident Response Planning under Model Misspecification through Bayesian Learning and Belief Quantization","created":"2025-08-20","cited_by_count":5,"area":null},{"id":"2510.06540","title":"Scalable Policy-Based RL Algorithms for POMDPs","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2509.06539","title":"Learning Optimal Defender Strategies for CAGE-2 using a POMDP Model","created":"2025-09-08","cited_by_count":3,"area":null},{"id":"2207.00818","title":"Geometric Learning of Hidden Markov Models via a Method of Moments Algorithm","created":"2022-07-02","cited_by_count":2,"area":null},{"id":"2212.02565","title":"Distributed Bayesian Learning of Dynamic States","created":"2022-12-05","cited_by_count":2,"area":null},{"id":"2505.11725","title":"CLT and Edgeworth Expansion for m-out-of-n Bootstrap Estimators of The Studentized Median","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2210.11444","title":"How can a Radar Mask its Cognition?","created":"2022-10-20","cited_by_count":1,"area":null},{"id":"2302.04151","title":"Policy Evaluation in Decentralized POMDPs with Belief Sharing","created":"2023-02-08","cited_by_count":1,"area":null},{"id":"2410.01331","title":"Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2108.11236","title":"Cell Multi-Bernoulli (Cell-MB) Sensor Control for Multi-object Search-While-Tracking (SWT)","created":"2021-08-25","cited_by_count":0,"area":null},{"id":"2501.18790","title":"Achieving $\\widetilde{\\mathcal{O}}(\\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2510.23905","title":"Inferring Group Intent as a Cooperative Game. An NLP-based Framework for Trajectory Analysis","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2512.20096","title":"Information-directed sampling for bandits: a primer","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2605.06346","title":"Prediction and Empowerment: A Theory of Agency through Bridge Interfaces","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2608.10729","title":"Optimal Stopping of Self-Refining Foundation Models","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.10298","title":"Learning Intrusion Response Strategies for OT Systems","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}