{"total":11,"rows":[{"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":"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":"2303.10302","title":"Welfare Maximization Algorithm for Solving Budget-Constrained Multi-Component POMDPs","created":"2023-03-18","cited_by_count":5,"area":null},{"id":"2109.08755","title":"Solving infinite-horizon Dec-POMDPs using Finite State Controllers within JESP","created":"2021-09-17","cited_by_count":4,"area":null},{"id":"2401.07656","title":"Learning Explainable and Better Performing Representations of POMDP Strategies","created":"2024-01-15","cited_by_count":4,"area":null},{"id":"2603.21399","title":"The Myhill-Nerode Theorem for Bounded Interaction: Canonical Abstractions via Agent-Bounded Indistinguishability","created":"2026-03-22","cited_by_count":3,"area":null},{"id":"2507.20951","title":"Partially Observable Monte-Carlo Graph Search","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2105.12249","title":"Bayesian Nonparametric Reinforcement Learning in LTE and Wi-Fi Coexistence","created":"2021-05-25","cited_by_count":0,"area":null},{"id":"2107.02431","title":"Bayesian Nonparametric Modelling for Model-Free Reinforcement Learning in LTE-LAA and Wi-Fi Coexistence","created":"2021-07-06","cited_by_count":0,"area":null},{"id":"2512.11082","title":"Memoryless Policy Iteration for Episodic POMDPs","created":"2025-12-11","cited_by_count":0,"area":null}],"next_cursor":null}