Optimal Off-Policy Evaluation from Multiple Logging Policies

• URL: http://arxiv.org/abs/2010.11002v1
• Date: Wed, 21 Oct 2020 13:43:48 GMT
• Title: Optimal Off-Policy Evaluation from Multiple Logging Policies
• Authors: Nathan Kallus, Yuta Saito, Masatoshi Uehara
• Abstract summary: We study off-policy evaluation from multiple logging policies, each generating a dataset of fixed size, i.e., stratified sampling. We find the OPE estimator for multiple loggers with minimum variance for any instance, i.e., the efficient one.
• Score: 77.62012545592233
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study off-policy evaluation (OPE) from multiple logging policies, each generating a dataset of fixed size, i.e., stratified sampling. Previous work noted that in this setting the ordering of the variances of different importance sampling estimators is instance-dependent, which brings up a dilemma as to which importance sampling weights to use. In this paper, we resolve this dilemma by finding the OPE estimator for multiple loggers with minimum variance for any instance, i.e., the efficient one. In particular, we establish the efficiency bound under stratified sampling and propose an estimator achieving this bound when given consistent $q$-estimates. To guard against misspecification of $q$-functions, we also provide a way to choose the control variate in a hypothesis class to minimize variance. Extensive experiments demonstrate the benefits of our methods' efficiently leveraging of the stratified sampling of off-policy data from multiple loggers.

Related papers

• Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach [51.76826149868971]
  Policy evaluation via Monte Carlo simulation is at the core of many MC Reinforcement Learning (RL) algorithms. We propose as a quality index a surrogate of the mean squared error of a return estimator that uses trajectories of different lengths. We present an adaptive algorithm called Robust and Iterative Data collection strategy Optimization (RIDO)
  arXiv  Detail & Related papers  (2024-10-17T11:47:56Z)
• Policy Gradient with Active Importance Sampling [55.112959067035916]
  Policy gradient (PG) methods significantly benefit from IS, enabling the effective reuse of previously collected samples. However, IS is employed in RL as a passive tool for re-weighting historical samples. We look for the best behavioral policy from which to collect samples to reduce the policy gradient variance.
  arXiv  Detail & Related papers  (2024-05-09T09:08:09Z)
• 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)
• Sample Dropout: A Simple yet Effective Variance Reduction Technique in Deep Policy Optimization [18.627233013208834]
  We show that the use of importance sampling could introduce high variance in the objective estimate. We propose a technique called sample dropout to bound the estimation variance by dropping out samples when their ratio deviation is too high.
  arXiv  Detail & Related papers  (2023-02-05T04:44:35Z)
• Bayesian Hierarchical Models for Counterfactual Estimation [12.159830463756341]
  We propose a probabilistic paradigm to estimate a diverse set of counterfactuals. We treat the perturbations as random variables endowed with prior distribution functions. A gradient based sampler with superior convergence characteristics efficiently computes the posterior samples.
  arXiv  Detail & Related papers  (2023-01-21T00:21:11Z)
• Quantile Off-Policy Evaluation via Deep Conditional Generative Learning [21.448553360543478]
  Off-Policy evaluation (OPE) is concerned with evaluating a new target policy using offline data generated by a potentially different behavior policy. We propose a doubly-robust inference procedure for quantile OPE in sequential decision making. We demonstrate the advantages of this proposed estimator through both simulations and a real-world dataset from a short-video platform.
  arXiv  Detail & Related papers  (2022-12-29T22:01:43Z)
• Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient [62.24615324523435]
  This paper provides a statistical analysis of high-dimensional batch Reinforcement Learning (RL) using sparse linear function approximation. When there is a large number of candidate features, our result sheds light on the fact that sparsity-aware methods can make batch RL more sample efficient.
  arXiv  Detail & Related papers  (2020-11-08T16:48:02Z)
• Multi-label Contrastive Predictive Coding [125.03510235962095]
  Variational mutual information (MI) estimators are widely used in unsupervised representation learning methods such as contrastive predictive coding (CPC) We introduce a novel estimator based on a multi-label classification problem, where the critic needs to jointly identify multiple positive samples at the same time. We show that using the same amount of negative samples, multi-label CPC is able to exceed the $log m$ bound, while still being a valid lower bound of mutual information.
  arXiv  Detail & Related papers  (2020-07-20T02:46:21Z)

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.