Uncertainty Quantification and Causal Considerations for Off-Policy Decision Making

• URL: http://arxiv.org/abs/2502.06011v1
• Date: Sun, 09 Feb 2025 20:05:19 GMT
• Title: Uncertainty Quantification and Causal Considerations for Off-Policy Decision Making
• Authors: Muhammad Faaiz Taufiq,
• Abstract summary: Off-policy evaluation (OPE) seeks to assess the performance of a new policy using data collected under a different policy. Existing OPE methodologies suffer from several limitations arising from statistical uncertainty as well as causal considerations. We introduce the Marginal Ratio (MR) estimator, a novel OPE method that reduces variance by focusing on the marginal distribution of outcomes. Next, we propose Conformal Off-Policy Prediction (COPP), a principled approach for uncertainty quantification in OPE. Finally, we address causal unidentifiability in off-policy decision-making by developing novel bounds for sequential decision settings
• Score: 4.514386953429771
• License:
• Abstract: Off-policy evaluation (OPE) is a critical challenge in robust decision-making that seeks to assess the performance of a new policy using data collected under a different policy. However, the existing OPE methodologies suffer from several limitations arising from statistical uncertainty as well as causal considerations. In this thesis, we address these limitations by presenting three different works. Firstly, we consider the problem of high variance in the importance-sampling-based OPE estimators. We introduce the Marginal Ratio (MR) estimator, a novel OPE method that reduces variance by focusing on the marginal distribution of outcomes rather than direct policy shifts, improving robustness in contextual bandits. Next, we propose Conformal Off-Policy Prediction (COPP), a principled approach for uncertainty quantification in OPE that provides finite-sample predictive intervals, ensuring robust decision-making in risk-sensitive applications. Finally, we address causal unidentifiability in off-policy decision-making by developing novel bounds for sequential decision settings, which remain valid under arbitrary unmeasured confounding. We apply these bounds to assess the reliability of digital twin models, introducing a falsification framework to identify scenarios where model predictions diverge from real-world behaviour. Our contributions provide new insights into robust decision-making under uncertainty and establish principled methods for evaluating policies in both static and dynamic settings.

Related papers

• 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)
• Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization [59.758009422067]
  We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning. We propose a new uncertainty Bellman equation (UBE) whose solution converges to the true posterior variance over values. We introduce a general-purpose policy optimization algorithm, Q-Uncertainty Soft Actor-Critic (QU-SAC) that can be applied for either risk-seeking or risk-averse policy optimization.
  arXiv  Detail & Related papers  (2023-12-07T15:55:58Z)
• Hallucinated Adversarial Control for Conservative Offline Policy Evaluation [64.94009515033984]
  We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, we seek to obtain a (tight) lower bound on a policy's performance. We introduce HAMBO, which builds on an uncertainty-aware learned model of the transition dynamics. We prove that the resulting COPE estimates are valid lower bounds, and, under regularity conditions, show their convergence to the true expected return.
  arXiv  Detail & Related papers  (2023-03-02T08:57:35Z)
• Identification of Subgroups With Similar Benefits in Off-Policy Policy Evaluation [60.71312668265873]
  We develop a method to balance the need for personalization with confident predictions. We show that our method can be used to form accurate predictions of heterogeneous treatment effects.
  arXiv  Detail & Related papers  (2021-11-28T23:19:12Z)
• Projected State-action Balancing Weights for Offline Reinforcement Learning [9.732863739456034]
  This paper focuses on the value estimation of a target policy based on pre-collected data generated from a possibly different policy. We propose a novel estimator with approximately projected state-action balancing weights for the policy value estimation. Numerical experiments demonstrate the promising performance of our proposed estimator.
  arXiv  Detail & Related papers  (2021-09-10T03:00:44Z)
• Offline Policy Selection under Uncertainty [113.57441913299868]
  We consider offline policy selection as learning preferences over a set of policy prospects given a fixed experience dataset. Access to the full distribution over one's belief of the policy value enables more flexible selection algorithms under a wider range of downstream evaluation metrics. We show how BayesDICE may be used to rank policies with respect to any arbitrary downstream policy selection metric.
  arXiv  Detail & Related papers  (2020-12-12T23:09:21Z)
• 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)
• Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies [80.42316902296832]
  We study the estimation of policy value and gradient of a deterministic policy from off-policy data when actions are continuous. In this setting, standard importance sampling and doubly robust estimators for policy value and gradient fail because the density ratio does not exist. We propose several new doubly robust estimators based on different kernelization approaches.
  arXiv  Detail & Related papers  (2020-06-06T15:52:05Z)
• Cautious Reinforcement Learning via Distributional Risk in the Dual Domain [45.17200683056563]
  We study the estimation of risk-sensitive policies in reinforcement learning problems defined by a Markov Decision Process (MDPs) whose state and action spaces are countably finite. We propose a new definition of risk, which we call caution, as a penalty function added to the dual objective of the linear programming (LP) formulation of reinforcement learning.
  arXiv  Detail & Related papers  (2020-02-27T23:18:04Z)

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.