Cover Image

Robustness Analysis of POMDP Policies to Observation Perturbations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kraske, Benjamin, Ho, Qi Heng, Rossi, Federico, Lahijanian, Morteza, Sunberg, Zachary
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Leveraging Counterfactual Paths for Contrastive Explanations of POMDP Policies
by: Kraske, Benjamin, et al.
Published: (2024)

Recursively-Constrained Partially Observable Markov Decision Processes
by: Ho, Qi Heng, et al.
Published: (2023)

Leveraging the Value of Information in POMDP Planning
by: Laouar, Zakariya, et al.
Published: (2026)

Sound Heuristic Search Value Iteration for Undiscounted POMDPs with Reachability Objectives
by: Ho, Qi Heng, et al.
Published: (2024)

Explanation through Reward Model Reconciliation using POMDP Tree Search
by: Kraske, Benjamin D., et al.
Published: (2023)

Sampling-based Task and Kinodynamic Motion Planning under Semantic Uncertainty
by: Ho, Qi Heng, et al.
Published: (2026)

Rao-Blackwellized POMDP Planning
by: Lee, Jiho, et al.
Published: (2024)

Resolving Multiple-Dynamic Model Uncertainty in Hypothesis-Driven Belief-MDPs
by: Dagan, Ofer, et al.
Published: (2024)

Bridging the Gap between Partially Observable Stochastic Games and Sparse POMDP Methods
by: Becker, Tyler, et al.
Published: (2024)

Online Pareto-Optimal Decision-Making for Complex Tasks using Active Inference
by: Amorese, Peter, et al.
Published: (2024)

Formal Verification of Unknown Dynamical Systems via Gaussian Process Regression
by: Skovbekk, John, et al.
Published: (2021)

Interval Markov Decision Processes with Continuous Action-Spaces
by: Delimpaltadakis, Giannis, et al.
Published: (2022)

Simplifying Complex Observation Models in Continuous POMDP Planning with Probabilistic Guarantees and Practice
by: Lev-Yehudi, Idan, et al.
Published: (2023)

Finite-Time Analysis of MCTS in Continuous POMDP Planning
by: Kong, Da, et al.
Published: (2026)

Vectorized Online POMDP Planning
by: Hoerger, Marcus, et al.
Published: (2025)

Kino-PAX$^+$: Near-Optimal Massively Parallel Kinodynamic Sampling-based Motion Planner
by: Perrault, Nicolas, et al.
Published: (2026)

Beyond Winning Strategies: Admissible and Admissible Winning Strategies for Quantitative Reachability Games
by: Muvvala, Karan, et al.
Published: (2024)

Kino-PAX: Highly Parallel Kinodynamic Sampling-based Planner
by: Perrault, Nicolas, et al.
Published: (2024)

POMDPPlanners: Open-Source Package for POMDP Planning
by: Pariente, Yaacov, et al.
Published: (2026)

Safe POMDP Online Planning via Shielding
by: Sheng, Shili, et al.
Published: (2023)

Distributionally Robust Policy Evaluation and Learning for Continuous Treatment with Observational Data
by: Leung, Cheuk Hang, et al.
Published: (2025)

MEMBOT: Memory-Based Robot in Intermittent POMDP
by: Liang, Youzhi, et al.
Published: (2025)

Measurement Simplification in ρ-POMDP with Performance Guarantees
by: Yotam, Tom, et al.
Published: (2023)

Approximate Dec-POMDP Solving Using Multi-Agent A*
by: Koops, Wietze, et al.
Published: (2024)

LLM-Guided Probabilistic Program Induction for POMDP Model Estimation
by: Curtis, Aidan, et al.
Published: (2025)

Addressing Myopic Constrained POMDP Planning with Recursive Dual Ascent
by: Stocco, Paula, et al.
Published: (2024)

Interval POMDP Shielding for Imperfect-Perception Agents
by: Scarbro, William, et al.
Published: (2026)

Synthesizing POMDP Policies: Sampling Meets Model-checking via Learning
by: Chakraborty, Debraj, et al.
Published: (2026)

Deep Belief Markov Models for POMDP Inference
by: Arcieri, Giacomo, et al.
Published: (2025)

Online POMDP Planning with Anytime Deterministic Optimality Guarantees
by: Barenboim, Moran, et al.
Published: (2023)

Error Bounds for Physics-Informed Neural Networks in Fokker-Planck PDEs
by: Kong, Chun-Wei, et al.
Published: (2024)

Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations
by: Eshwar, S. R., et al.
Published: (2025)

Learning Symbolic Persistent Macro-Actions for POMDP Solving Over Time
by: Veronese, Celeste, et al.
Published: (2025)

Investigating the Robustness of Sequential Recommender Systems Against Training Data Perturbations
by: Betello, Filippo, et al.
Published: (2023)

GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
by: Li, Zaitang, et al.
Published: (2023)

Towards Intention Recognition for Robotic Assistants Through Online POMDP Planning
by: Saborio, Juan Carlos, et al.
Published: (2024)

Anytime Incremental $ρ$POMDP Planning in Continuous Spaces
by: Benchetrit, Ron, et al.
Published: (2025)

Expert-Guided POMDP Learning for Data-Efficient Modeling in Healthcare
by: Locatelli, Marco, et al.
Published: (2025)

Provably Safe Motion Planning Under Unknown Disturbances
by: Gracia, Ibon, et al.
Published: (2026)

Policy Gradient for Robust Markov Decision Processes
by: Wang, Qiuhao, et al.
Published: (2024)