OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators

• URL: http://arxiv.org/abs/2405.17708v2
• Date: Thu, 31 Oct 2024 23:40:16 GMT
• Title: OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators
• Authors: Allen Nie, Yash Chandak, Christina J. Yuan, Anirudhan Badrinath, Yannis Flet-Berliac, Emma Brunskil,
• Abstract summary: offline policy evaluation (OPE) allows us to evaluate and estimate a new sequential decision-making policy's performance. We propose a new algorithm that adaptively blends a set of OPE estimators given a dataset without relying on an explicit selection using a statistical procedure. Our work contributes to improving ease of use for a general-purpose, estimator-agnostic, off-policy evaluation framework for offline RL.
• Score: 13.408838970377035
• License:
• Abstract: Offline policy evaluation (OPE) allows us to evaluate and estimate a new sequential decision-making policy's performance by leveraging historical interaction data collected from other policies. Evaluating a new policy online without a confident estimate of its performance can lead to costly, unsafe, or hazardous outcomes, especially in education and healthcare. Several OPE estimators have been proposed in the last decade, many of which have hyperparameters and require training. Unfortunately, choosing the best OPE algorithm for each task and domain is still unclear. In this paper, we propose a new algorithm that adaptively blends a set of OPE estimators given a dataset without relying on an explicit selection using a statistical procedure. We prove that our estimator is consistent and satisfies several desirable properties for policy evaluation. Additionally, we demonstrate that when compared to alternative approaches, our estimator can be used to select higher-performing policies in healthcare and robotics. Our work contributes to improving ease of use for a general-purpose, estimator-agnostic, off-policy evaluation framework for offline RL.

Related papers

• Automated Off-Policy Estimator Selection via Supervised Learning [7.476028372444458]
  Off-Policy Evaluation (OPE) problem consists of evaluating the performance of counterfactual policies with data collected by another one. To solve the OPE problem, we resort to estimators, which aim to estimate in the most accurate way possible the performance that the counterfactual policies would have had if they were deployed in place of the logging policy. We propose an automated data-driven OPE estimator selection method based on supervised learning.
  arXiv  Detail & Related papers  (2024-06-26T02:34:48Z)
• Uncertainty-Aware Instance Reweighting for Off-Policy Learning [63.31923483172859]
  We propose a Uncertainty-aware Inverse Propensity Score estimator (UIPS) for improved off-policy learning. Experiment results on synthetic and three real-world recommendation datasets demonstrate the advantageous sample efficiency of the proposed UIPS estimator.
  arXiv  Detail & Related papers  (2023-03-11T11:42:26Z)
• Data-Driven Off-Policy Estimator Selection: An Application in User Marketing on An Online Content Delivery Service [11.986224119327387]
  Off-policy evaluation is essential in domains such as healthcare, marketing or recommender systems. Many OPE methods with theoretical backgrounds have been proposed. It is often unknown for practitioners which estimator to use for their specific applications and purposes.
  arXiv  Detail & Related papers  (2021-09-17T15:53:53Z)
• Evaluating the Robustness of Off-Policy Evaluation [10.760026478889664]
  Off-policy Evaluation (OPE) evaluates the performance of hypothetical policies leveraging only offline log data. It is particularly useful in applications where the online interaction involves high stakes and expensive setting. We develop Interpretable Evaluation for Offline Evaluation (IEOE), an experimental procedure to evaluate OPE estimators' robustness.
  arXiv  Detail & Related papers  (2021-08-31T09:33:13Z)
• Active Offline Policy Selection [19.18251239758809]
  This paper addresses the problem of policy selection in domains with abundant logged data, but with a very restricted interaction budget. Several off-policy evaluation (OPE) techniques have been proposed to assess the value of policies using only logged data. We introduce a novel emphactive offline policy selection problem formulation, which combined logged data and limited online interactions to identify the best policy.
  arXiv  Detail & Related papers  (2021-06-18T17:33:13Z)
• Benchmarks for Deep Off-Policy Evaluation [152.28569758144022]
  We present a collection of policies that can be used for benchmarking off-policy evaluation. The goal of our benchmark is to provide a standardized measure of progress that is motivated from a set of principles. We provide open-source access to our data and code to foster future research in this area.
  arXiv  Detail & Related papers  (2021-03-30T18:09:33Z)
• MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning [108.79676336281211]
  Continuous deployment of new policies for data collection and online learning is either cost ineffective or impractical. We propose a new algorithmic learning framework called Model-based Uncertainty regularized and Sample Efficient Batch Optimization. Our framework discovers novel and high quality samples for each deployment to enable efficient data collection.
  arXiv  Detail & Related papers  (2021-02-23T01:30:55Z)
• 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)
• Accountable Off-Policy Evaluation With Kernel Bellman Statistics [29.14119984573459]
  We consider off-policy evaluation (OPE), which evaluates the performance of a new policy from observed data collected from previous experiments. Due to the limited information from off-policy data, it is highly desirable to construct rigorous confidence intervals, not just point estimation. We propose a new variational framework which reduces the problem of calculating tight confidence bounds in OPE.
  arXiv  Detail & Related papers  (2020-08-15T07:24:38Z)
• Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation [49.502277468627035]
  This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history.
  arXiv  Detail & Related papers  (2020-02-21T19:20:57Z)
• Efficient Policy Learning from Surrogate-Loss Classification Reductions [65.91730154730905]
  We consider the estimation problem given by a weighted surrogate-loss classification reduction of policy learning. We show that, under a correct specification assumption, the weighted classification formulation need not be efficient for policy parameters. We propose an estimation approach based on generalized method of moments, which is efficient for the policy parameters.
  arXiv  Detail & Related papers  (2020-02-12T18:54:41Z)

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.