mlsanityData to 14 Oct 2026

Adversarial observations in probabilistic State-Space Models for robust Reinforcement Learning

arXiv 2606.20880 ↗First posted 18 Jun 2026stat.ML cs.LG stat.MEcited by 0

On the map: Deep reinforcement learning methods → Adversarial robustness and RL in finance

Abstract (arXiv)

Decision-making under partial or adversarial observability requires accurate inference of the environment's latent state and its associated uncertainty. This work analyses adversarial attacks on linear state-space models, where the attacker alters observations subject to likelihood constraints that ensure that the perturbations remain statistically consistent with the observation model. We analyse how such adversarial yet plausible observations shift inference about latent states and affect downstream decision-making and the performance of reinforcement learning agents. In addition, we introduce an online Bayesian defence based on directional covariance adaptation, which selectively reduces the influence of observations by comparing their estimated impact with that of the computed most disruptive direction, while preserving information in the remaining orthogonal observation subspace. The proposed framework provides a principled approach to constructing robust inference and decision-making systems, with direct relevance to safety-critical applications such as robotics, where reliable operation under sensor noise, partial failures, and adversarial conditions is essential.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods. Builds on 27 of its 55 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

27 of 55 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Adversarial Inception Backdoor Attacks against Reinforcement Learning17 Oct

Other references · 26

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
  6. 2021Convex optimizationcited by 2,515
  7. 2021Efficiently Modeling Long Sequences with Structured State Spacescited by 2,465
  8. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  9. 2022Simplified State Space Layers for Sequence Modelingcited by 788
  10. 2017Robust Adversarial Reinforcement Learningcited by 451
  11. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 414
  12. 2017Adversarial Attacks on Neural Network Policiescited by 320
14 more
  1. 2019Adversarial Policies: Attacking Deep Reinforcement Learningcited by 214
  2. 2023Structured State Space Models for In-Context Reinforcement Learningcited by 111
  3. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 94
  4. 2017Vulnerability of Deep Reinforcement Learning to Policy Induction Attackscited by 91
  5. 2024Outlier-robust Kalman Filtering through Generalised Bayescited by 21
  6. 2018Wasserstein Distributionally Robust Kalman Filteringcited by 17
  7. 2025Advancing Intelligent Sequence Modeling: Evolution, Trade-offs, and Applications of State-Space Architectures from S4 to Mambacited by 9
  8. 2020Adversarial Machine Learning: Bayesian Perspectivescited by 8
  9. 2024Uncertainty Representations in State-Space Layers for Deep Reinforcement Learning under Partial Observabilitycited by 5
  10. 2024A unifying framework for generalised Bayesian online learning in non-stationary environmentscited by 5
  11. 2014Secure State Estimation For Cyber Physical Systems Under Sensor Attacks: A Satisfiability Modulo Theory Approachcited by 2
  12. 2013Variational Bayesian Adaptation of Noise Covariances in Non-Linear Kalman Filteringcited by 1
  13. 2017Robust Bayesian Filtering and Smoothing Using Student's t Distributioncited by 1
  14. 2024Distributionally Robust Kalman Filtering over Finite and Infinite Horizoncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards Robust Policy: Enhancing Offline Reinforcement Learning with Adversarial Attacks and Defenses
  2. 2026Adversarial Latent-State Training for Robust Policies in Partially Observable Domains
  3. 2025Towards Optimal Adversarial Robust Reinforcement Learning with Infinity Measurement Error
  4. 2024Robust off-policy Reinforcement Learning via Soft Constrained Adversary
  5. 2026Robust Adversarial Policy Optimization Under Dynamics Uncertainty
  6. 2026Robust Policy Optimization via Adversarial Importance Sampling
  7. 2025Towards Robust Deep Reinforcement Learning against Environmental State Perturbation
  8. 2026Robust Adversarial Reinforcement Learning with Risk Sensitivity and Critic Consistency Regularization