Off-Policy Evaluation with Strategic Agents via Local Disclosure

• URL: http://arxiv.org/abs/2606.07308v1
• Date: Fri, 05 Jun 2026 14:24:50 GMT
• Title: Off-Policy Evaluation with Strategic Agents via Local Disclosure
• Abstract summary: We study off-policy evaluation (OPE) under strategic behavior.<n>We find that local information reveals agents' pre-strategic covariates prior to adaptation.<n>Our results highlight how interaction design can mitigate information asymmetry by revealing otherwise hidden structure in agents' strategic responses.
• Score: 19.10069019048424
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study off-policy evaluation (OPE) under strategic behavior where decision subjects (or agents) respond to a decision maker's policy by strategically modifying their covariates. Such behavior induces a policy-dependent covariate shift, breaking the standard assumption in existing methods that covariates are exogenous to the policy. Related work addresses this challenge by imposing strong assumptions such as repeated interactions or full knowledge of agents' response behavior, substantially limiting its applicability to OPE. In contrast, we consider a one-shot OPE setting where the decision maker has only partial knowledge of the agents' response behavior. Our key insight is that disclosing local information through post-hoc explanations reveals agents' pre-strategic covariates prior to adaptation, mitigating the information loss induced by strategic behavior. Leveraging this structure, we estimate a statistical model for the agents' responses and construct a doubly robust estimator for policy value. By assuming that the agents' cost sensitivity follows a conditional log-normal distribution, we establish consistency of the proposed estimator and validate our approach empirically. More broadly, our results highlight how interaction design can mitigate information asymmetry by revealing otherwise hidden structure in agents' strategic responses.

Related papers

• Strategic Feature Selection [62.74494413516484]
  We study strategic classification through feature selection and its interaction with ridge regularization.<n>We provide a fine-grained characterization of the performance of a feature subset under optimal regularization.<n>Motivated by this characterization, we develop a practical algorithm for jointly choosing the feature set and the level of ridge regularization.
  arXiv  Detail & Related papers  (2026-06-17T09:47:15Z)
• Beyond Rational Illusion: Behaviorally Realistic Strategic Classification [56.458581740660236]
  We propose the Prospect-Guided Strategic Framework (Pro-SF) to address the behaviorally realistic strategic classification problem.<n>Pro-SF is a principled framework grounded in prospect theory to model and learn under behaviorally realistic strategic responses.<n> Experiments on synthetic and real-world datasets establish Pro-SF as a behaviorally grounded approach to strategic classification.
  arXiv  Detail & Related papers  (2026-05-19T11:04:55Z)
• The Reciprocity Gradient [52.35929743862925]
  Communication is fundamental to sustaining reciprocity and cooperation in strategic interactions.<n>We identify and formulate the influence attribution problem as the central optimization difficulty inherent in such dynamics for a learning agent.<n>To address this, we introduce the reciprocity gradient, which explicitly backpropagates reward gradients through private estimators of opponents' policies trained from public observations.
  arXiv  Detail & Related papers  (2026-05-08T16:29:52Z)
• Effective Red-Teaming of Policy-Adherent Agents [10.522087614181745]
  Task-oriented LLM-based agents are increasingly used in domains with strict policies, such as refund eligibility or cancellation rules.<n>We propose a novel threat model that focuses on adversarial users aiming to exploit policy-adherent agents for personal benefit.<n>We present CRAFT, a multi-agent red-teaming system that leverages policy-aware persuasive strategies to undermine a policy-adherent agent in a customer-service scenario.
  arXiv  Detail & Related papers  (2025-06-11T10:59:47Z)
• Uncertainty Quantification and Causal Considerations for Off-Policy Decision Making [4.514386953429771]
  Off-policy evaluation (OPE) seeks to assess the performance of a new policy using data collected under a different policy.<n>Existing OPE methodologies suffer from several limitations arising from statistical uncertainty as well as causal considerations.<n>We introduce the Marginal Ratio (MR) estimator, a novel OPE method that reduces variance by focusing on the marginal distribution of outcomes.<n>Next, we propose Conformal Off-Policy Prediction (COPP), a principled approach for uncertainty quantification in OPE.<n>Finally, we address causal unidentifiability in off-policy decision-making by developing novel bounds for sequential decision settings
  arXiv  Detail & Related papers  (2025-02-09T20:05:19Z)
• Explanation Design in Strategic Learning: Sufficient Explanations that Induce Non-harmful Responses [29.57116418734347]
  Key open question is how DMs can communicate explanations in a way that avoids harming strategic agents.<n>We prove that action recommendation-based explanations (ARexes) are sufficient for non-harmful responses.<n>Experiments show that ARexes allow the DM to optimise their model's predictive performance while preserving agents' utility.
  arXiv  Detail & Related papers  (2025-02-06T13:17:24Z)
• Predictive Performance Comparison of Decision Policies Under Confounding [32.21041697921289]
  We propose a method to compare the predictive performance of decision policies under a variety of modern identification approaches. Key to our method is the insight that there are regions of uncertainty that we can safely ignore in the policy comparison.
  arXiv  Detail & Related papers  (2024-04-01T01:27:07Z)
• On the Value of Myopic Behavior in Policy Reuse [67.37788288093299]
  Leveraging learned strategies in unfamiliar scenarios is fundamental to human intelligence. In this work, we present a framework called Selective Myopic bEhavior Control(SMEC) SMEC adaptively aggregates the sharable short-term behaviors of prior policies and the long-term behaviors of the task policy, leading to coordinated decisions.
  arXiv  Detail & Related papers  (2023-05-28T03:59:37Z)
• Policy Learning with Competing Agents [2.972870935419738]
  Decision makers often aim to learn a treatment assignment policy under a capacity constraint on the number of agents that they can treat.<n>In this paper, we study capacity-constrained treatment assignment in the presence of such interference.
  arXiv  Detail & Related papers  (2022-04-04T23:15:00Z)
• Privacy-Constrained Policies via Mutual Information Regularized Policy Gradients [54.98496284653234]
  We consider the task of training a policy that maximizes reward while minimizing disclosure of certain sensitive state variables through the actions. We solve this problem by introducing a regularizer based on the mutual information between the sensitive state and the actions. We develop a model-based estimator for optimization of privacy-constrained policies.
  arXiv  Detail & Related papers  (2020-12-30T03:22:35Z)
• Learning Goal-oriented Dialogue Policy with Opposite Agent Awareness [116.804536884437]
  We propose an opposite behavior aware framework for policy learning in goal-oriented dialogues. We estimate the opposite agent's policy from its behavior and use this estimation to improve the target agent by regarding it as part of the target policy.
  arXiv  Detail & Related papers  (2020-04-21T03:13:44Z)

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.