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

• URL: http://arxiv.org/abs/2606.20880v1
• Date: Thu, 18 Jun 2026 19:15:06 GMT
• Title: Adversarial observations in probabilistic State-Space Models for robust Reinforcement Learning
• Abstract summary: Decision-making under partial or adversarial observability requires accurate inference of the environment's latent state and its associated uncertainty.<n>This work analyses adversarial attacks on linear probabilistic state-space models, commonly integrated within reinforcement learning architectures.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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 probabilistic state-space models, commonly integrated within reinforcement learning architectures, where the attacker alters observations under likelihood constraints that ensure the perturbations remains consistent. We analyze how such adversarial yet realistic observation shifts influence the latent state and influence policy decisions. This perspective provides a principled pathway toward building more robust reinforcement learning systems, with direct relevance to safety-critical domains such as robotics, where reliable operation under sensor noise, partial failures, and adversarial conditions is essential.

Related papers

• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations [55.76952683833966]
  This paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC) to reduce confidence set size when data may be corrupted.<n>Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size.
  arXiv  Detail & Related papers  (2026-07-29T05:16:59Z)
• Anticipatory Reinforcement Learning: From Generative Path-Laws to Distributional Value Functions [0.0]
  This paper introduces Anticipatory Reinforcement Learning (ARL), a novel framework designed to bridge the gap between non-Markovian decision processes and classical reinforcement learning architectures.<n>In environments characterised by jump-diffusions and structural breaks, traditional state-based methods often fail to capture the essential path-dependent geometry required for accurate foresight.
  arXiv  Detail & Related papers  (2026-04-06T13:15:44Z)
• Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry [19.669339224904277]
  A vital risk is intrinsic deception, wherein models strategically mislead users to achieve their own objectives.<n>Existing alignment approaches based on chain-of-thought (CoT) monitoring supervise explicit reasoning traces.<n>We propose Stability Asymmetry Regularization (SAR), a novel alignment objective that penalizes this distributional asymmetry during reinforcement learning.
  arXiv  Detail & Related papers  (2026-03-27T09:47:57Z)
• State-Dependent Safety Failures in Multi-Turn Language Model Interaction [70.52906620450847]
  We study safety failures from a state-space perspective and show that many multi-turn failures arise from structured contextual state evolution.<n>We introduce STAR, a state-oriented diagnostic framework that treats dialogue history as a state transition operator.<n>We find that systems that appear robust under static evaluation can undergo rapid and reproducible safety collapse under structured multi-turn interaction.
  arXiv  Detail & Related papers  (2026-03-15T12:13:01Z)
• Sim2Act: Robust Simulation-to-Decision Learning via Adversarial Calibration and Group-Relative Perturbation [54.29523408543184]
  Simulation-to-decision learning enables safe policy training in digital environments without risking real-world deployment.<n>Existing approaches either focus on improving average simulation fidelity or adopt conservative regularization.<n>We propose Sim2Act, a robust simulation-to-decision framework that addresses both simulator and policy robustness.
  arXiv  Detail & Related papers  (2026-03-10T00:51:47Z)
• Transformer-Based Reinforcement Learning for Autonomous Orbital Collision Avoidance in Partially Observable Environments [0.3093890460224435]
  We introduce a Transformer-based Reinforcement Learning framework for autonomous orbital collision avoidance.<n>A central contribution of this work is the use of transformer-based Partially Observable Markov Decision Process architecture.<n>This integration provides a foundation for training collision avoidance agents that can operate more reliably under imperfect monitoring environments.
  arXiv  Detail & Related papers  (2026-02-05T04:57:58Z)
• Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint [52.878820730054365]
  Instruction Fine-Tuning (IFT) has been widely adopted as an effective post-training strategy to enhance abilities of Large Language Models (LLMs)<n>Recent research into the internal mechanisms of LLMs has identified the refusal direction (r-direction) in the hidden states, which plays a pivotal role in governing refusal behavior.<n>To mitigate such drift, our proposed ProCon method introduces a projection-constrained loss term that regularizes the projection magnitude of each training sample's hidden state onto the r-direction.
  arXiv  Detail & Related papers  (2025-09-08T15:24:33Z)
• Enhancing Uncertainty Quantification for Runtime Safety Assurance Using Causal Risk Analysis and Operational Design Domain [0.0]
  We propose an enhancement of traditional uncertainty quantification by explicitly incorporating environmental conditions.<n>We leverage Hazard Analysis and Risk Assessment (HARA) and fault tree modeling to identify critical operational conditions affecting system functionality.<n>At runtime, this BN is instantiated using real-time environmental observations to infer a probabilistic distribution over the safety estimation.
  arXiv  Detail & Related papers  (2025-07-04T12:12:32Z)
• Realistic Adversarial Attacks for Robustness Evaluation of Trajectory Prediction Models via Future State Perturbation [1.124958340749622]
  Trajectory prediction is a key element of autonomous vehicle systems.<n>Current approaches tend to focus on perturbing the past positions of surrounding agents.<n>We introduce new performance measures to assess the realism and impact of these adversarial trajectories.
  arXiv  Detail & Related papers  (2025-05-09T15:40:32Z)
• Benchmarking the Spatial Robustness of DNNs via Natural and Adversarial Localized Corruptions [49.546479320670464]
  This paper introduces specialized metrics for benchmarking the spatial robustness of segmentation models.<n>We propose region-aware multi-attack adversarial analysis, a method that enables a deeper understanding of model robustness.<n>The results reveal that models respond to these two types of threats differently.
  arXiv  Detail & Related papers  (2025-04-02T11:37:39Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)

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.