Robustness Analysis of POMDP Policies to Observation Perturbations

• URL: http://arxiv.org/abs/2604.21256v1
• Date: Thu, 23 Apr 2026 03:57:08 GMT
• Title: Robustness Analysis of POMDP Policies to Observation Perturbations
• Abstract summary: This work studies policy robustness against deviations in the POMDP observation model.<n>We introduce the Policy Observation Robustness Problem: to determine the maximum deviation in a POMDP's observation model.<n>We present Robust Interval Search, an algorithm with soundness and convergence guarantees, for both the sticky and non-sticky variants.
• Score: 12.74304759862804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Policies for Partially Observable Markov Decision Processes (POMDPs) are often designed using a nominal system model. In practice, this model can deviate from the true system during deployment due to factors such as calibration drift or sensor degradation, leading to unexpected performance degradation. This work studies policy robustness against deviations in the POMDP observation model. We introduce the Policy Observation Robustness Problem: to determine the maximum tolerable deviation in a POMDP's observation model that guarantees the policy's value remains above a specified threshold. We analyze two variants: the sticky variant, where deviations are dependent on state and actions, and the non-sticky variant, where they can be history-dependent. We show that the Policy Observation Robustness Problem can be formulated as a bi-level optimization problem in which the inner optimization is monotonic in the size of the observation deviation. This enables efficient solutions using root-finding algorithms in the outer optimization. For the non-sticky variant, we show that when policies are represented with finite-state controllers (FSCs) it is sufficient to consider observations which depend on nodes in the FSC rather than full histories. We present Robust Interval Search, an algorithm with soundness and convergence guarantees, for both the sticky and non-sticky variants. We show this algorithm has polynomial time complexity in the non-sticky variant and at most exponential time complexity in the sticky variant. We provide experimental results validating and demonstrating the scalability of implementations of Robust Interval Search to POMDP problems with tens of thousands of states. We also provide case studies from robotics and operations research which demonstrate the practical utility of the problem and algorithms.

Related papers

• When Sensors Fail: Temporal Sequence Models for Robust PPO under Sensor Drift [64.37959940809633]
  We study robustness of Proximal Policy Optimization (PPO) under temporally persistent sensor failures.<n>We show Transformer-based sequence policies substantially outperform, RNN, and SSMs in robustness, maintaining high returns even when large fractions of sensors are unavailable.
  arXiv  Detail & Related papers  (2026-03-04T22:21:54Z)
• Learning Robust Penetration-Testing Policies under Partial Observability: A systematic evaluation [0.28675177318965045]
  Penetration testing, the simulation of cyberattacks to identify security vulnerabilities, presents a sequential decision-making problem.<n>Partial observability invalidates the Markov property present in Markov Decision Processes.<n>We investigate, partially observable penetration testing scenarios over host networks of varying size, aiming to better reflect real-world complexity.
  arXiv  Detail & Related papers  (2025-09-24T11:27:54Z)
• Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting [56.92178753201331]
  We propose the Observation-Aware Spectral (OAS) estimation technique, which enables the POMDP parameters to be learned from samples collected using a belief-based policy. We show the consistency of the OAS procedure, and we prove a regret guarantee of order $mathcalO(sqrtT log(T)$ for the proposed OAS-UCRL algorithm.
  arXiv  Detail & Related papers  (2024-10-02T08:46:34Z)
• Sound Heuristic Search Value Iteration for Undiscounted POMDPs with Reachability Objectives [16.101435842520473]
  This paper studies the challenging yet important problem in POMDPs known as the (indefinite-horizon) Maximal Reachability Probability Problem. Inspired by the success of point-based methods developed for discounted problems, we study their extensions to MRPP. We present a novel algorithm that leverages the strengths of these techniques for efficient exploration of the belief space.
  arXiv  Detail & Related papers  (2024-06-05T02:33:50Z)
• Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes [44.974100402600165]
  We study the evaluation of a policy best-parametric and worst-case perturbations to a decision process (MDP) We use transition observations from the original MDP, whether they are generated under the same or a different policy. Our estimator is also estimated statistical inference using Wald confidence intervals.
  arXiv  Detail & Related papers  (2024-03-29T18:11:49Z)
• Online POMDP Planning with Anytime Deterministic Optimality Guarantees [13.824288326240927]
  We derive a deterministic relationship for discrete POMDPs between an approximated and the optimal solution.<n>We show that our derivations provide an avenue for a new set of algorithms and can be attached to existing algorithms.
  arXiv  Detail & Related papers  (2023-10-03T04:40:38Z)
• Nearly Optimal Latent State Decoding in Block MDPs [74.51224067640717]
  In episodic Block MDPs, the decision maker has access to rich observations or contexts generated from a small number of latent states. We are first interested in estimating the latent state decoding function based on data generated under a fixed behavior policy. We then study the problem of learning near-optimal policies in the reward-free framework.
  arXiv  Detail & Related papers  (2022-08-17T18:49:53Z)
• A general sample complexity analysis of vanilla policy gradient [101.16957584135767]
  Policy gradient (PG) is one of the most popular reinforcement learning (RL) problems. "vanilla" theoretical understanding of PG trajectory is one of the most popular methods for solving RL problems.
  arXiv  Detail & Related papers  (2021-07-23T19:38:17Z)
• Robust Value Iteration for Continuous Control Tasks [99.00362538261972]
  When transferring a control policy from simulation to a physical system, the policy needs to be robust to variations in the dynamics to perform well. We present Robust Fitted Value Iteration, which uses dynamic programming to compute the optimal value function on the compact state domain. We show that robust value is more robust compared to deep reinforcement learning algorithm and the non-robust version of the algorithm.
  arXiv  Detail & Related papers  (2021-05-25T19:48:35Z)
• Near Optimality of Finite Memory Feedback Policies in Partially Observed Markov Decision Processes [0.0]
  We study a planning problem for POMDPs where the system dynamics and measurement channel model is assumed to be known. We find optimal policies for the approximate belief model under mild non-linear filter stability conditions. We also establish a rate of convergence result which relates the finite window memory size and the approximation error bound.
  arXiv  Detail & Related papers  (2020-10-15T00:37:51Z)
• Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis [102.29671176698373]
  We address the problem of policy evaluation in discounted decision processes, and provide Markov-dependent guarantees on the $ell_infty$error under a generative model. We establish both and non-asymptotic versions of local minimax lower bounds for policy evaluation, thereby providing an instance-dependent baseline by which to compare algorithms.
  arXiv  Detail & Related papers  (2020-03-16T17:15:28Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.