{"total":21,"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":"2301.04939","title":"Safe Policy Improvement for POMDPs via Finite-State Controllers","created":"2023-01-12","cited_by_count":12,"area":null},{"id":"2303.05848","title":"Decision-Making Under Uncertainty: Beyond Probabilities","created":"2023-03-10","cited_by_count":9,"area":null},{"id":"2408.08770","title":"Pessimistic Iterative Planning with RNNs for Robust POMDPs","created":"2024-08-16","cited_by_count":7,"area":null},{"id":"2201.08772","title":"Under-Approximating Expected Total Rewards in POMDPs","created":"2022-01-21","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":"2109.07436","title":"Computing Policies That Account For The Effects Of Human Agent Uncertainty During Execution In Markov Decision Processes","created":"2021-09-15","cited_by_count":3,"area":null},{"id":"2110.12810","title":"Learning What to Memorize: Using Intrinsic Motivation to Form Useful Memory in Partially Observable Reinforcement Learning","created":"2021-10-25","cited_by_count":1,"area":null},{"id":"2302.13916","title":"Robust Robot Planning for Human-Robot Collaboration","created":"2023-02-27","cited_by_count":1,"area":null},{"id":"2305.11811","title":"Monte-Carlo Search for an Equilibrium in Dec-POMDPs","created":"2023-05-19","cited_by_count":1,"area":null},{"id":"2507.20951","title":"Partially Observable Monte-Carlo Graph Search","created":"2025-07-28","cited_by_count":1,"area":null},{"id":"2512.03204","title":"Scaling Internal-State Policy-Gradient Methods for POMDPs","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2604.01024","title":"Model-Based Learning of Near-Optimal Finite-Window Policies in POMDPs","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2106.08849","title":"How memory architecture affects learning in a simple POMDP: the two-hypothesis testing problem","created":"2021-06-16","cited_by_count":0,"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":"2409.11671","title":"Anticipating Oblivious Opponents in Stochastic Games","created":"2024-09-18","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},{"id":"2604.21256","title":"Robustness Analysis of POMDP Policies to Observation Perturbations","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2610.15010","title":"On the Complexity Gap Between POMDPs and Multi-Environment POMDPs","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}