{"total":21,"rows":[{"id":"2102.07850","title":"Differentiable Particle Filtering via Entropy-Regularized Optimal Transport","created":"2021-02-15","cited_by_count":59,"area":null},{"id":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36,"area":null},{"id":"2105.07593","title":"Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation","created":"2021-05-17","cited_by_count":34,"area":null},{"id":"2407.07788","title":"BiGym: A Demo-Driven Mobile Bi-Manual Manipulation Benchmark","created":"2024-07-10","cited_by_count":30,"area":null},{"id":"2302.09639","title":"An overview of differentiable particle filters for data-adaptive sequential Bayesian inference","created":"2023-02-19","cited_by_count":23,"area":null},{"id":"2110.12628","title":"Recurrent Off-policy Baselines for Memory-based Continuous Control","created":"2021-10-25","cited_by_count":21,"area":null},{"id":"2110.13549","title":"Online Variational Filtering and Parameter Learning","created":"2021-10-26","cited_by_count":19,"area":null},{"id":"2211.01991","title":"Leveraging Fully Observable Policies for Learning under Partial Observability","created":"2022-11-03","cited_by_count":18,"area":null},{"id":"2403.01499","title":"Normalizing Flow-based Differentiable Particle Filters","created":"2024-03-03","cited_by_count":10,"area":null},{"id":"2105.06228","title":"SIDE: State Inference for Partially Observable Cooperative Multi-Agent Reinforcement Learning","created":"2021-05-13","cited_by_count":7,"area":null},{"id":"2109.15134","title":"Variational Marginal Particle Filters","created":"2021-09-30","cited_by_count":6,"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":"2212.06968","title":"Particle-Based Score Estimation for State Space Model Learning in Autonomous Driving","created":"2022-12-14","cited_by_count":3,"area":null},{"id":"2307.11954","title":"On-Robot Bayesian Reinforcement Learning for POMDPs","created":"2023-07-22","cited_by_count":3,"area":null},{"id":"2401.17752","title":"PF-GNN: Differentiable particle filtering based approximation of universal graph representations","created":"2024-01-31","cited_by_count":3,"area":null},{"id":"2412.12024","title":"Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps","created":"2024-12-16","cited_by_count":2,"area":null},{"id":"2202.08884","title":"BADDr: Bayes-Adaptive Deep Dropout RL for POMDPs","created":"2022-02-17","cited_by_count":1,"area":null},{"id":"2510.10709","title":"Missing Data Multiple Imputation for Tabular Q-Learning in Online RL","created":"2025-10-12","cited_by_count":1,"area":null},{"id":"2510.21107","title":"ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2602.05679","title":"Perception-Based Beliefs for POMDPs with Visual Observations","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2305.16639","title":"Universal Approximation and the Topological Neural Network","created":"2023-05-26","cited_by_count":0,"area":null}],"next_cursor":null}