{"total":84,"rows":[{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135,"area":null},{"id":"2209.10342","title":"Partially Observable Markov Decision Processes in Robotics: A Survey","created":"2022-09-21","cited_by_count":86,"area":null},{"id":"2205.06750","title":"Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking","created":"2022-05-13","cited_by_count":34,"area":null},{"id":"2402.17930","title":"Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning","created":"2024-02-27","cited_by_count":28,"area":null},{"id":"2210.05015","title":"Optimality Guarantees for Particle Belief Approximation of POMDPs","created":"2022-10-10","cited_by_count":20,"area":null},{"id":"2206.06553","title":"Safe Output Feedback Motion Planning from Images via Learned Perception Modules and Contraction Theory","created":"2022-06-14","cited_by_count":19,"area":null},{"id":"2601.14354","title":"VJEPA: Variational Joint Embedding Predictive Architectures as Probabilistic World Models","created":"2026-01-20","cited_by_count":17,"area":"wm"},{"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":"2109.13570","title":"Adaptive Informative Path Planning Using Deep Reinforcement Learning for UAV-based Active Sensing","created":"2021-09-28","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":"2410.11234","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","created":"2024-10-15","cited_by_count":11,"area":"offlinerl"},{"id":"2112.09456","title":"Compositional Learning-based Planning for Vision POMDPs","created":"2021-12-17","cited_by_count":8,"area":null},{"id":"2405.00644","title":"ConstrainedZero: Chance-Constrained POMDP Planning using Learned Probabilistic Failure Surrogates and Adaptive Safety Constraints","created":"2024-05-01","cited_by_count":8,"area":null},{"id":"2210.13455","title":"Epistemic Monte Carlo Tree Search","created":"2022-10-21","cited_by_count":7,"area":null},{"id":"2310.15288","title":"Active teacher selection for reward learning","created":"2023-10-23","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":"2212.00669","title":"A POMDP Model for Safe Geological Carbon Sequestration","created":"2022-10-25","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":"2203.16777","title":"Mask Atari for Deep Reinforcement Learning as POMDP Benchmarks","created":"2022-03-31","cited_by_count":5,"area":null},{"id":"2212.12154","title":"Online Planning for Constrained POMDPs with Continuous Spaces through Dual Ascent","created":"2022-12-23","cited_by_count":5,"area":null},{"id":"2401.15315","title":"Learning Online Belief Prediction for Efficient POMDP Planning in Autonomous Driving","created":"2024-01-27","cited_by_count":5,"area":"driving"},{"id":"2103.11345","title":"Monte Carlo Information-Oriented Planning","created":"2021-03-21","cited_by_count":4,"area":null},{"id":"2105.05296","title":"Online POMDP Planning via Simplification","created":"2021-05-11","cited_by_count":4,"area":null},{"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":"2209.07660","title":"Sequential Bayesian Optimization for Adaptive Informative Path Planning with Multimodal Sensing","created":"2022-09-16","cited_by_count":4,"area":null},{"id":"2302.06697","title":"Simplified Continuous High Dimensional Belief Space Planning with Adaptive Probabilistic Belief-dependent Constraints","created":"2023-02-13","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":"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":"2307.08774","title":"Reflections from the Workshop on AI-Assisted Decision Making for Conservation","created":"2023-07-17","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":"2410.03892","title":"Towards Cost Sensitive Decision Making","created":"2024-10-04","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":"2507.21846","title":"Probabilistic Active Goal Recognition","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2601.20554","title":"Online Risk-Averse Planning in POMDPs Using Iterated CVaR Value Function","created":"2026-01-28","cited_by_count":2,"area":null},{"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":"2305.11811","title":"Monte-Carlo Search for an Equilibrium in Dec-POMDPs","created":"2023-05-19","cited_by_count":1,"area":null},{"id":"2305.16056","title":"Reinforcement Learning under External Influence: Guarantees, Algorithms, and Sample Complexity","created":"2023-05-25","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":"2310.20054","title":"Constrained Hierarchical Monte Carlo Belief-State Planning","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2410.17967","title":"POMDP-Driven Cognitive Massive MIMO Radar: Joint Target Detection-Tracking In Unknown Disturbances","created":"2024-10-23","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":"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":"2512.01977","title":"AI-Driven Optimization under Uncertainty for Mineral Processing Operations","created":"2025-12-01","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":"2209.11591","title":"involve-MI: Informative Planning with High-Dimensional Non-Parametric Beliefs","created":"2022-09-23","cited_by_count":0,"area":null},{"id":"2211.02700","title":"Achieving mouse-level strategic evasion performance using real-time computational planning","created":"2022-11-04","cited_by_count":0,"area":null},{"id":"2303.16821","title":"Decision Making for Autonomous Driving in Interactive Merge Scenarios via Learning-based Prediction","created":"2023-03-29","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":"2405.02605","title":"MEXGEN: An Effective and Efficient Information Gain Approximation for Information Gathering Path Planning","created":"2024-05-04","cited_by_count":0,"area":null},{"id":"2411.06711","title":"Anytime Probabilistically Constrained Provably Convergent Online Belief Space Planning","created":"2024-11-11","cited_by_count":0,"area":null},{"id":"2501.17982","title":"Belief Roadmaps with Uncertain Landmark Evanescence","created":"2025-01-29","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":"2505.11698","title":"Conditional Deep Generative Models for Belief State Planning","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2506.08434","title":"Attention-based Learning for 3D Informative Path Planning","created":"2025-06-10","cited_by_count":0,"area":"deeprl"},{"id":"2507.12186","title":"Partially Observable Reference Policy Programming: Solving POMDPs Sans Numerical Optimisation","created":"2025-07-16","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":"2512.06002","title":"POrTAL: Plan-Orchestrated Tree Assembly for Lookahead","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2602.19315","title":"Online Navigation Planning for Long-term Autonomous Operation of Underwater Gliders","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2602.20810","title":"POMDPPlanners: Open-Source Package for POMDP Planning","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2604.01434","title":"Leveraging the Value of Information in POMDP Planning","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2605.07703","title":"Finite-Time Analysis of MCTS in Continuous POMDP Planning","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.18598","title":"Optimizing Lithium Production Decisions under Geological, Demand, and Pricing Uncertainties: A POMDP Framework for Multi-Objective Decision Making","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.19729","title":"VOiLA: Vectorized Online Planning with Learned Diffusion Models for POMDP Agents","created":"2026-06-18","cited_by_count":0,"area":"diffusion"},{"id":"2606.21971","title":"REBA: A Revealed Belief Automaton Framework for Online Planning in Continuous POMDPs","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.03155","title":"Hope for the Best, Prepare for the Worst: Occlusion-Aware Contingency Planning for Autonomous Vehicles","created":"2026-07-03","cited_by_count":0,"area":"driving"},{"id":"2607.16981","title":"Expected Free Energy as Belief-Dependent Utility for rho-POMDPs","created":"2026-07-18","cited_by_count":0,"area":null},{"id":"2609.01351","title":"Scalable Rao-Blackwellized Online Planning for High-Dimensional POMDPs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.13428","title":"Chance-Constrained Belief-Space Maneuver Planning for Autonomous Collision Avoidance Under Uncertainty","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.35874","title":"Risk-Averse Online POMDP Planning via CVaR of the Immediate Cost with Performance Guarantees","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.15046","title":"Belief Embedding Tree Search","created":"2026-10-10","cited_by_count":0,"area":null}],"next_cursor":null}