{"total":106,"rows":[{"id":"2303.09824","title":"Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives","created":"2023-03-17","cited_by_count":114,"area":"driving"},{"id":"2209.10342","title":"Partially Observable Markov Decision Processes in Robotics: A Survey","created":"2022-09-21","cited_by_count":86,"area":null},{"id":"2106.15691","title":"Deep Multiagent Reinforcement Learning: Challenges and Directions","created":"2021-06-29","cited_by_count":42,"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":"2307.07527","title":"Machine Learning for Autonomous Vehicle's Trajectory Prediction: A comprehensive survey, Challenges, and Future Research Directions","created":"2023-07-12","cited_by_count":23,"area":"driving"},{"id":"2210.05015","title":"Optimality Guarantees for Particle Belief Approximation of POMDPs","created":"2022-10-10","cited_by_count":20,"area":null},{"id":"2107.02349","title":"Physical Interaction as Communication: Learning Robot Objectives Online from Human Corrections","created":"2021-07-06","cited_by_count":19,"area":null},{"id":"2408.14336","title":"Equivariant Reinforcement Learning under Partial Observability","created":"2024-08-26","cited_by_count":18,"area":"deeprl"},{"id":"2306.15136","title":"What Truly Matters in Trajectory Prediction for Autonomous Driving?","created":"2023-06-27","cited_by_count":17,"area":null},{"id":"2403.10454","title":"Partially Observable Task and Motion Planning with Uncertainty and Risk Awareness","created":"2024-03-15","cited_by_count":17,"area":null},{"id":"1806.03820","title":"An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning","created":"2018-06-11","cited_by_count":15,"area":"offlinerl"},{"id":"2101.04237","title":"Solving Common-Payoff Games with Approximate Policy Iteration","created":"2021-01-11","cited_by_count":15,"area":null},{"id":"2302.00171","title":"Active Uncertainty Reduction for Safe and Efficient Interaction Planning: A Shielding-Aware Dual Control Approach","created":"2023-02-01","cited_by_count":15,"area":null},{"id":"2110.09991","title":"Towards Optimal Correlational Object Search","created":"2021-10-19","cited_by_count":14,"area":null},{"id":"2306.00249","title":"BetaZero: Belief-State Planning for Long-Horizon POMDPs using Learned Approximations","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2101.03834","title":"Closing the Planning-Learning Loop with Application to Autonomous Driving","created":"2021-01-11","cited_by_count":12,"area":"driving"},{"id":"2304.06848","title":"CAR-DESPOT: Causally-Informed Online POMDP Planning for Robots in Confounded Environments","created":"2023-04-13","cited_by_count":12,"area":null},{"id":"2202.07720","title":"Active Uncertainty Reduction for Human-Robot Interaction: An Implicit Dual Control Approach","created":"2022-02-15","cited_by_count":10,"area":null},{"id":"2209.11422","title":"LEADER: Learning Attention over Driving Behaviors for Planning under Uncertainty","created":"2022-09-23","cited_by_count":9,"area":"driving"},{"id":"2112.09456","title":"Compositional Learning-based Planning for Vision POMDPs","created":"2021-12-17","cited_by_count":8,"area":null},{"id":"2309.10216","title":"Safe POMDP Online Planning via Shielding","created":"2023-09-19","cited_by_count":8,"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":"2303.09172","title":"Learning Logic Specifications for Soft Policy Guidance in POMCP","created":"2023-03-16","cited_by_count":7,"area":null},{"id":"2105.14239","title":"Simplified Belief-Dependent Reward MCTS Planning with Guaranteed Tree Consistency","created":"2021-05-29","cited_by_count":6,"area":null},{"id":"2201.05673","title":"Adaptive Information Belief Space Planning","created":"2022-01-14","cited_by_count":6,"area":null},{"id":"2205.07767","title":"Efficient Algorithms for Planning with Participation Constraints","created":"2022-05-16","cited_by_count":6,"area":null},{"id":"2211.14983","title":"Multiagent Reinforcement Learning for Autonomous Routing and Pickup Problem with Adaptation to Variable Demand","created":"2022-11-28","cited_by_count":6,"area":null},{"id":"2302.00797","title":"Combining Tree-Search, Generative Models, and Nash Bargaining Concepts in Game-Theoretic Reinforcement Learning","created":"2023-02-01","cited_by_count":6,"area":null},{"id":"2302.10439","title":"Adaptive Discretization using Voronoi Trees for Continuous POMDPs","created":"2023-02-21","cited_by_count":6,"area":null},{"id":"2406.03641","title":"Task and Motion Planning for Execution in the Real","created":"2024-06-05","cited_by_count":6,"area":null},{"id":"2203.16777","title":"Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2207.08096","title":"Nonmyopic Distilled Data Association Belief Space Planning Under Budget Constraints","created":"2022-07-17","cited_by_count":5,"area":null},{"id":"2105.05296","title":"Online POMDP Planning via Simplification","created":"2021-05-11","cited_by_count":4,"area":null},{"id":"2107.03600","title":"Reinforcement Learning based Negotiation-aware Motion Planning of Autonomous Vehicles","created":"2021-07-08","cited_by_count":4,"area":"driving"},{"id":"2206.10028","title":"Intention-Aware Navigation in Crowds with Extended-Space POMDP Planning","created":"2022-06-20","cited_by_count":4,"area":null},{"id":"2312.03263","title":"Weathering Ongoing Uncertainty: Learning and Planning in a Time-Varying Partially Observable Environment","created":"2023-12-06","cited_by_count":4,"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":"2209.02679","title":"Risk Aware Adaptive Belief-dependent Probabilistically Constrained Continuous POMDP Planning","created":"2022-09-06","cited_by_count":3,"area":null},{"id":"2209.05733","title":"Adaptive Discretization using Voronoi Trees for Continuous-Action POMDPs","created":"2022-09-13","cited_by_count":3,"area":null},{"id":"2310.01791","title":"Online POMDP Planning with Anytime Deterministic Optimality Guarantees","created":"2023-10-03","cited_by_count":3,"area":null},{"id":"2502.05690","title":"Managing Geological Uncertainty in Critical Mineral Supply Chains: A POMDP Approach with Application to U.S. Lithium Resources","created":"2025-02-08","cited_by_count":3,"area":null},{"id":"2505.15863","title":"Generative AI for Autonomous Driving: A Review","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2103.13860","title":"Active Inference Tree Search in Large POMDPs","created":"2021-03-25","cited_by_count":2,"area":null},{"id":"2105.05789","title":"Probabilistic Loss and its Online Characterization for Simplified Decision Making Under Uncertainty","created":"2021-05-12","cited_by_count":2,"area":null},{"id":"2106.04206","title":"Efficient Sampling in POMDPs with Lipschitz Bandits for Motion Planning in Continuous Spaces","created":"2021-06-08","cited_by_count":2,"area":null},{"id":"2110.10324","title":"HARPS: An Online POMDP Framework for Human-Assisted Robotic Planning and Sensing","created":"2021-10-20","cited_by_count":2,"area":null},{"id":"2211.07735","title":"Monte Carlo Planning in Hybrid Belief POMDPs","created":"2022-11-14","cited_by_count":2,"area":null},{"id":"2310.02345","title":"Rollout Heuristics for Online Stochastic Contingent Planning","created":"2023-10-03","cited_by_count":2,"area":null},{"id":"2311.07745","title":"Simplifying Complex Observation Models in Continuous POMDP Planning with Probabilistic Guarantees and Practice","created":"2023-11-13","cited_by_count":2,"area":null},{"id":"2409.18411","title":"Hi-Drive: Hierarchical POMDP Planning for Safe Autonomous Driving in Diverse Urban Environments","created":"2024-09-27","cited_by_count":2,"area":null},{"id":"2410.03892","title":"Towards Cost Sensitive Decision Making","created":"2024-10-04","cited_by_count":2,"area":null},{"id":"2410.12172","title":"The State of Robot Motion Generation","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2411.12967","title":"Shrinking POMCP: A Framework for Real-Time UAV Search and Rescue","created":"2024-11-20","cited_by_count":2,"area":null},{"id":"2412.02570","title":"TAB-Fields: A Maximum Entropy Framework for Mission-Aware Adversarial Planning","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2412.13128","title":"Previous Knowledge Utilization In Online Anytime Belief Space Planning","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2503.19302","title":"Observation Adaptation via Annealed Importance Resampling for Partially Observable Markov Decision Processes","created":"2025-03-25","cited_by_count":2,"area":null},{"id":"2505.03668","title":"Learning Symbolic Persistent Macro-Actions for POMDP Solving Over Time","created":"2025-05-06","cited_by_count":2,"area":"lr"},{"id":"2510.27191","title":"Vectorized Online POMDP Planning","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2104.07276","title":"Adaptive Belief Discretization for POMDP Planning","created":"2021-04-15","cited_by_count":1,"area":null},{"id":"2207.13181","title":"Planning and Learning: Path-Planning for Autonomous Vehicles, a Review of the Literature","created":"2022-07-26","cited_by_count":1,"area":"driving"},{"id":"2209.05580","title":"Risk-aware Meta-level Decision Making for Exploration Under Uncertainty","created":"2022-09-12","cited_by_count":1,"area":null},{"id":"2303.02139","title":"Data Association Aware POMDP Planning with Hypothesis Pruning Performance Guarantees","created":"2023-03-03","cited_by_count":1,"area":null},{"id":"2304.09352","title":"Optimizing Carbon Storage Operations for Long-Term Safety","created":"2023-04-19","cited_by_count":1,"area":null},{"id":"2305.00931","title":"Explanation through Reward Model Reconciliation using POMDP Tree Search","created":"2023-05-01","cited_by_count":1,"area":"alignment"},{"id":"2307.02637","title":"Surge Routing: Event-informed Multiagent Reinforcement Learning for Autonomous Rideshare","created":"2023-07-05","cited_by_count":1,"area":null},{"id":"2309.10701","title":"Measurement Simplification in \\rho-POMDP with Performance Guarantees","created":"2023-09-19","cited_by_count":1,"area":null},{"id":"2310.10274","title":"No Compromise in Solution Quality: Speeding Up Belief-dependent Continuous POMDPs via Adaptive Multilevel Simplification","created":"2023-10-16","cited_by_count":1,"area":null},{"id":"2407.16962","title":"Toward an Integrated Decision Making Framework for Optimized Stroke Diagnosis with DSA and Treatment under Uncertainty","created":"2024-07-24","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":"2409.13754","title":"Increasing the Value of Information During Planning in Uncertain Environments","created":"2024-09-14","cited_by_count":1,"area":null},{"id":"2410.05870","title":"Heuristics for Partially Observable Stochastic Contingent Planning","created":"2024-10-08","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":"2508.12166","title":"Belief-Conditioned One-Step Diffusion: Real-Time Trajectory Planning with Just-Enough Sensing","created":"2025-08-16","cited_by_count":1,"area":null},{"id":"2509.10162","title":"Online Robust Planning under Model Uncertainty: A Sample-Based Approach","created":"2025-09-12","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":"2603.00785","title":"QANTIS: A Hardware-Validated Quantum Platform for POMDP Planning and Multi-Target Data Association","created":"2026-02-28","cited_by_count":1,"area":null},{"id":"2606.10376","title":"Belief-Space Control for Personalized Cancer Treatment via Active Inference","created":"2026-06-09","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":"2201.11404","title":"Online Planning in POMDPs with Self-Improving Simulators","created":"2022-01-27","cited_by_count":0,"area":null},{"id":"2207.09713","title":"Towards Plug'n Play Task-Level Autonomy for Robotics Using POMDPs and Generative Models","created":"2022-07-20","cited_by_count":0,"area":null},{"id":"2209.11591","title":"involve-MI: Informative Planning with High-Dimensional Non-Parametric Beliefs","created":"2022-09-23","cited_by_count":0,"area":null},{"id":"2303.06768","title":"The Planner Optimization Problem: Formulations and Frameworks","created":"2023-03-12","cited_by_count":0,"area":null},{"id":"2304.10984","title":"IBBT: Informed Batch Belief Trees for Motion Planning Under Uncertainty","created":"2023-04-21","cited_by_count":0,"area":null},{"id":"2305.08049","title":"A Surprisingly Simple Continuous-Action POMDP Solver: Lazy Cross-Entropy Search Over Policy Trees","created":"2023-05-14","cited_by_count":0,"area":null},{"id":"2312.11434","title":"Factored Online Planning in Many-Agent POMDPs","created":"2023-12-18","cited_by_count":0,"area":null},{"id":"2402.01431","title":"Approximate Control for Continuous-Time POMDPs","created":"2024-02-02","cited_by_count":0,"area":null},{"id":"2403.19760","title":"Leveraging Counterfactual Paths for Contrastive Explanations of POMDP Policies","created":"2024-03-28","cited_by_count":0,"area":null},{"id":"2405.15907","title":"Belief-State Query Policies for User-Aligned POMDPs","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2503.12181","title":"Action-Gradient Monte Carlo Tree Search for Non-Parametric Continuous (PO)MDPs","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2508.21314","title":"Convergence of regularized agent-state-based Q-learning in POMDPs","created":"2025-08-29","cited_by_count":0,"area":"deeprl"},{"id":"2509.18407","title":"Assistive Decision-Making for Right of Way Navigation at Uncontrolled Intersections","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2510.14035","title":"GammaZero: Learning To Guide POMDP Belief Space Search With Graph Representations","created":"2025-10-15","cited_by_count":0,"area":null},{"id":"2511.08825","title":"Neural Value Iteration","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2512.06002","title":"POrTAL: Plan-Orchestrated Tree Assembly for Lookahead","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2602.08334","title":"Vec-QMDP: Vectorized POMDP Planning on CPUs for Real-Time Autonomous Driving","created":"2026-02-09","cited_by_count":0,"area":"driving"},{"id":"2604.01434","title":"Leveraging the Value of Information in POMDP Planning","created":"2026-04-01","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":"2605.14440","title":"Synthesizing POMDP Policies: Sampling Meets Model-checking via Learning","created":"2026-05-14","cited_by_count":0,"area":null}],"next_cursor":"100"}