Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability

• URL: http://arxiv.org/abs/2605.14246v1
• Date: Thu, 14 May 2026 01:23:09 GMT
• Title: Action-Conditioned Risk Gating for Safety-Critical Control under Partial Observability
• Abstract summary: We propose a lightweight risk-gated reinforcement learning approximation for risk-sensitive control under partial observability.<n>We evaluate the approach in two safety-critical partially observable domains: automated glucose regulation and safety-constrained navigation.
• Score: 79.08785366532287
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many safety-critical control problems are modeled as risk-sensitive partially observable Markov decision processes, where the controller must make decisions from incomplete observations while balancing task performance against safety risk. Although belief-space planning provides a principled solution, maintaining and planning over beliefs can be computationally costly and sensitive to model specification in practical domains. We propose a lightweight risk-gated reinforcement learning approximation for risk-sensitive control under partial observability. The method constructs a compact finite-history proxy state and learns an action-conditioned predictor of near-term safety violation. This predicted candidate-action risk is used in two complementary ways: as a risk penalty during value learning, and as a decision-time gate that interpolates between optimistic and conservative ensemble value estimates. As a result, low-risk actions are evaluated closer to reward-seeking estimates, while high-risk actions are evaluated more conservatively. We evaluate the approach in two safety-critical partially observable domains: automated glucose regulation and safety-constrained navigation. Across adult and adolescent glucose-control cohorts, the method improves overall glycemic tradeoffs and substantially reduces runtime relative to a belief-space planning baseline. On Safety-Gym navigation benchmarks, it achieves a more favorable reward-cost balance than unconstrained RL and several standard safe-RL baselines. These results suggest that action-conditioned near-term risk can provide an effective local signal for approximate risk-sensitive POMDP control when full belief-space planning is impractical.

Related papers

• Quantifying Risk Under Evolving Uncertainty: Belief-Dependent Robustness for Safe Sequential Decision Making [0.0]
  We propose RATTL (Risk-Adrial Total-Reward Learning), which ties caution to uncertainty.<n>We show the resulting planning problem is well posed under transience and compactness conditions.<n>RATTL targets safety for agents, including runtime-based systems, acting under uncertainty.
  arXiv  Detail & Related papers  (2026-08-18T09:36:19Z)
• Risk-Constrained Belief-Space Optimization for Safe Control under Latent Uncertainty [5.99447754429793]
  Many safety-critical control systems must operate under latent uncertainty that sensors cannot directly resolve at decision time.<n>Standard methods optimize expected performance and offer limited protection against rare but severe outcomes.<n>We consider partially observed dynamical systems whose dynamics, costs, and safety constraints depend on a latent parameter maintained as a belief distribution.
  arXiv  Detail & Related papers  (2026-04-04T21:22:44Z)
• Safe Probabilistic Planning for Human-Robot Interaction using Conformal Risk Control [13.455001736850255]
  We present a novel probabilistic safe control framework for human-robot interaction.<n>The approach uses conformal risk control to quantify and control the prediction errors in CBF safety values.<n>We demonstrate that our approach significantly reduces collision rates and safety violations as compared to baseline methods.
  arXiv  Detail & Related papers  (2026-03-11T04:19:44Z)
• Conformal Thinking: Risk Control for Reasoning on a Compute Budget [60.65072883773352]
  Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy improving as the token budget increases.<n>We re-frame the budget setting problem as risk control, limiting the error rate while minimizing compute.<n>Our framework introduces an upper threshold that stops reasoning when the model is confident and a novel lower threshold that preemptively stops unsolvable instances.
  arXiv  Detail & Related papers  (2026-02-03T18:17:22Z)
• Self-Guard: Defending Large Reasoning Models via enhanced self-reflection [54.775612141528164]
  Self-Guard is a lightweight safety defense framework for Large Reasoning Models.<n>It bridges the awareness-compliance gap, achieving robust safety performance without compromising model utility.<n>Self-Guard exhibits strong generalization across diverse unseen risks and varying model scales.
  arXiv  Detail & Related papers  (2026-01-31T13:06:11Z)
• Constrained Language Model Policy Optimization via Risk-aware Stepwise Alignment [49.2305683068875]
  We propose Risk-aware Stepwise Alignment (RSA), a novel alignment method that incorporates risk awareness into the policy optimization process.<n> RSA mitigates risks induced by excessive model shift away from a reference policy, and it explicitly suppresses low-probability yet high-impact harmful behaviors.<n> Experimental results demonstrate that our method achieves high levels of helpfulness while ensuring strong safety.
  arXiv  Detail & Related papers  (2025-12-30T14:38:02Z)
• Conformal Risk Training: End-to-End Optimization of Conformal Risk Control [41.45834526675908]
  We introduce "conformal risk training," an end-to-end approach that differentiates through conformal OCE risk control during model training or fine-tuning.<n>Our method achieves provable risk guarantees while demonstrating significantly improved average-case performance over post-hoc approaches.
  arXiv  Detail & Related papers  (2025-10-09T19:05:45Z)
• RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration [81.38705556267917]
  Existing safety evaluation methods for large language models (LLMs) suffer from inherent limitations.<n>We introduce a theoretical framework that reconstructs the underlying risk concept space.<n>We propose RADAR, a multi-agent collaborative evaluation framework.
  arXiv  Detail & Related papers  (2025-09-28T09:35:32Z)
• ConstrainedZero: Chance-Constrained POMDP Planning using Learned Probabilistic Failure Surrogates and Adaptive Safety Constraints [34.9739641898452]
  This work introduces the ConstrainedZero policy algorithm that solves CC-POMDPs in belief space by learning neural network approximations of the optimal value and policy. Results show that by separating safety constraints from the objective we can achieve a target level of safety without optimizing the balance between rewards and costs.
  arXiv  Detail & Related papers  (2024-05-01T17:17:22Z)
• Safety Margins for Reinforcement Learning [53.10194953873209]
  We show how to leverage proxy criticality metrics to generate safety margins. We evaluate our approach on learned policies from APE-X and A3C within an Atari environment.
  arXiv  Detail & Related papers  (2023-07-25T16:49:54Z)

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.