Conformal Policy Learning with Distribution-Free Safety Guarantees

• URL: http://arxiv.org/abs/2609.17296v1
• Date: Tue, 15 Sep 2026 15:08:03 GMT
• Title: Conformal Policy Learning with Distribution-Free Safety Guarantees
• Abstract summary: Policy learning aims to determine who should be treated based on individual characteristics.<n>In high-stakes settings such as medicine and public policy where safety is a central concern, improving the average outcomes alone may not be sufficient.<n>We propose textitconformal policy learning (CPL), a policy learning procedure with a new distribution-free safety guarantee.
• Score: 8.587200177311516
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Policy learning aims to determine who should be treated based on individual characteristics. In high-stakes settings such as medicine and public policy where safety is a central concern, improving the average outcomes alone may not be sufficient: decision makers may also seek to protect individuals from harm, in line with the Hippocratic principle of ``do no harm.'' In this paper, we propose \textit{conformal policy learning} (CPL), a policy learning procedure with a new distribution-free safety guarantee that controls the probability of assigning treatment to an individual who would be harmed relative to control. CPL views each treatment decision as testing a hypothesis of counterfactual harm and assigns treatment by thresholding conformal p-values. These p-values use observable proxies and selective calibration to address the challenge that the potential outcomes under comparison are never simultaneously observed. For randomized experiments, under standard exchangeability conditions, CPL provides finite-sample safety guarantee at a user-specified level, without imposing any outcome modeling assumptions. Moreover, when the outcome model is consistently estimated, CPL achieves asymptotically optimal welfare subject to the safety constraint. In observational studies, CPL with learn-then-balance weights achieves doubly robust safety guarantees. We evaluate CPL through extensive simulations and apply it to an empirical study of AI-powered interventions designed to reduce conspiracy beliefs.

Related papers

• Topological Feasibility Guarantees for Differentiable Predictive Control [0.8880611506199766]
  Differentiable predictive control (DPC) is a self-supervised learning approach for approximating explicit model predictive control (MPC) policies.<n> feasibility guarantees, a core requirement for safe control, are currently provided either probabilistically or via online safety filters.<n>This paper establishes deterministic feasibility guarantees for DPC using a novel topological analysis of the induced reachable safe set.
  arXiv  Detail & Related papers  (2026-08-11T00:27:50Z)
• PAC-Bayesian Reward-Certified Outcome Weighted Learning [0.0]
  Estimating optimal individualized treatment rules (ITRs) via outcome weighted learning (OWL) often relies on observed rewards that are noisy or optimistic proxies for the true latent utility.<n>We propose PAC-Bayesian Reward-Certified Outcome Weighted Learning (PROWL)<n>Given a one-sided uncertainty certificate, PROWL constructs a conservative reward and a strictly policy-dependent lower bound on the true expected value.
  arXiv  Detail & Related papers  (2026-04-02T12:08:56Z)
• 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)
• SAFER: Risk-Constrained Sample-then-Filter in Large Language Models [38.97678256807034]
  We introduce a two-stage risk control framework comprising abstention-aware sampling and conformalized filtering.<n>We show that SAFER is compatible with various task-specific admission criteria and calibration-test split ratios.
  arXiv  Detail & Related papers  (2025-10-11T12:12:41Z)
• Learning Deterministic Policies with Policy Gradients in Constrained Markov Decision Processes [59.27926064817273]
  We introduce an exploration-agnostic algorithm, called C-PG, which enjoys global last-iterate convergence guarantees under domination assumptions.<n>We empirically validate both the action-based (C-PGAE) and parameter-based (C-PGPE) variants of C-PG on constrained control tasks.
  arXiv  Detail & Related papers  (2025-06-06T10:29:05Z)
• SPoRt -- Safe Policy Ratio: Certified Training and Deployment of Task Policies in Model-Free RL [54.022106606140774]
  We present theoretical results that place a bound on the probability of violating a safety property for a new task-specific policy in a model-free, episodic setting.<n>This bound can be applied to temporally-extended properties (beyond safety) and to robust control problems.<n>We present experimental results demonstrating this trade-off and comparing the theoretical bound to posterior bounds derived from empirical violation rates.
  arXiv  Detail & Related papers  (2025-04-08T19:09:07Z)
• Proximal Ranking Policy Optimization for Practical Safety in Counterfactual Learning to Rank [64.44255178199846]
  We propose a novel approach, proximal ranking policy optimization (PRPO), that provides safety in deployment without assumptions about user behavior. PRPO removes incentives for learning ranking behavior that is too dissimilar to a safe ranking model. Our experiments show that PRPO provides higher performance than the existing safe inverse propensity scoring approach.
  arXiv  Detail & Related papers  (2024-09-15T22:22:27Z)
• How Generalizable Is My Behavior Cloning Policy? A Statistical Approach to Trustworthy Performance Evaluation [17.638831964639834]
  Behavior cloning policies are increasingly successful at solving complex tasks by learning from human demonstrations. We present a framework that provides a tight lower-bound on robot performance in an arbitrary environment. In experiments we evaluate policies for visuomotor manipulation in both simulation and hardware.
  arXiv  Detail & Related papers  (2024-05-08T22:00:35Z)
• A Risk-Sensitive Approach to Policy Optimization [21.684251937825234]
  Standard deep reinforcement learning (DRL) aims to maximize expected reward, considering collected experiences equally in formulating a policy. We propose a more direct approach whereby risk-sensitive objectives, specified in terms of the cumulative distribution function (CDF) of the distribution of full-episode rewards, are optimized. We demonstrate that the use of moderately "pessimistic" risk profiles, which emphasize scenarios where the agent performs poorly, leads to enhanced exploration and a continual focus on addressing deficiencies.
  arXiv  Detail & Related papers  (2022-08-19T00:55:05Z)
• Conformal Off-Policy Prediction in Contextual Bandits [54.67508891852636]
  Conformal off-policy prediction can output reliable predictive intervals for the outcome under a new target policy. We provide theoretical finite-sample guarantees without making any additional assumptions beyond the standard contextual bandit setup.
  arXiv  Detail & Related papers  (2022-06-09T10:39:33Z)
• Reliable Off-policy Evaluation for Reinforcement Learning [53.486680020852724]
  In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy. We propose a novel framework that provides robust and optimistic cumulative reward estimates using one or multiple logged data.
  arXiv  Detail & Related papers  (2020-11-08T23:16:19Z)

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.