{"total":21,"rows":[{"id":"2209.10342","title":"Partially Observable Markov Decision Processes in Robotics: A Survey","created":"2022-09-21","cited_by_count":86,"area":null},{"id":"2206.03446","title":"Learning in Observable POMDPs, without Computationally Intractable Oracles","created":"2022-06-07","cited_by_count":30,"area":null},{"id":"2201.04735","title":"Planning in Observable POMDPs in Quasipolynomial Time","created":"2022-01-12","cited_by_count":25,"area":null},{"id":"2505.02216","title":"LLM-Guided Probabilistic Program Induction for POMDP Model Estimation","created":"2025-05-04","cited_by_count":12,"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":"2303.09172","title":"Learning Logic Specifications for Soft Policy Guidance in POMCP","created":"2023-03-16","cited_by_count":7,"area":null},{"id":"2402.19265","title":"Learning Logic Specifications for Policy Guidance in POMDPs: an Inductive Logic Programming Approach","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2303.10302","title":"Welfare Maximization Algorithm for Solving Budget-Constrained Multi-Component POMDPs","created":"2023-03-18","cited_by_count":5,"area":null},{"id":"2308.09041","title":"A Mathematical Characterization of Minimally Sufficient Robot Brains","created":"2023-08-17","cited_by_count":5,"area":null},{"id":"2505.16732","title":"Sequential Monte Carlo for Policy Optimization in Continuous POMDPs","created":"2025-05-22","cited_by_count":4,"area":null},{"id":"2207.00368","title":"Multi-Objective Coordination Graphs for the Expected Scalarised Returns with Generative Flow Models","created":"2022-07-01","cited_by_count":3,"area":null},{"id":"2302.11761","title":"Intermittently Observable Markov Decision Processes","created":"2023-02-23","cited_by_count":3,"area":null},{"id":"2104.13791","title":"Rule-based Shielding for Partially Observable Monte-Carlo Planning","created":"2021-04-28","cited_by_count":2,"area":null},{"id":"2106.03926","title":"Reconciling Rewards with Predictive State Representations","created":"2021-06-07","cited_by_count":1,"area":null},{"id":"2108.13965","title":"Approximation Methods for Partially Observed Markov Decision Processes (POMDPs)","created":"2021-08-31","cited_by_count":1,"area":null},{"id":"2304.10246","title":"Filter-Aware Model-Predictive Control","created":"2023-04-20","cited_by_count":1,"area":null},{"id":"2407.18812","title":"Online Planning in POMDPs with State-Requests","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2411.17326","title":"Towards Intention Recognition for Robotic Assistants Through Online POMDP Planning","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2505.03280","title":"MDPs with a State Sensing Cost","created":"2025-05-06","cited_by_count":1,"area":null},{"id":"2303.07397","title":"Fast exploration and learning of latent graphs with aliased observations","created":"2023-03-13","cited_by_count":0,"area":null},{"id":"2304.04346","title":"A Novel Point-based Algorithm for Multi-agent Control Using the Common Information Approach","created":"2023-04-10","cited_by_count":0,"area":null}],"next_cursor":null}