GenDICE: Generalized Offline Estimation of Stationary Values

• URL: http://arxiv.org/abs/2002.09072v1
• Date: Fri, 21 Feb 2020 00:27:52 GMT
• Title: GenDICE: Generalized Offline Estimation of Stationary Values
• Authors: Ruiyi Zhang, Bo Dai, Lihong Li, Dale Schuurmans
• Abstract summary: We show that effective estimation can still be achieved in important applications. Our approach is based on estimating a ratio that corrects for the discrepancy between the stationary and empirical distributions. The resulting algorithm, GenDICE, is straightforward and effective.
• Score: 108.17309783125398
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: An important problem that arises in reinforcement learning and Monte Carlo methods is estimating quantities defined by the stationary distribution of a Markov chain. In many real-world applications, access to the underlying transition operator is limited to a fixed set of data that has already been collected, without additional interaction with the environment being available. We show that consistent estimation remains possible in this challenging scenario, and that effective estimation can still be achieved in important applications. Our approach is based on estimating a ratio that corrects for the discrepancy between the stationary and empirical distributions, derived from fundamental properties of the stationary distribution, and exploiting constraint reformulations based on variational divergence minimization. The resulting algorithm, GenDICE, is straightforward and effective. We prove its consistency under general conditions, provide an error analysis, and demonstrate strong empirical performance on benchmark problems, including off-line PageRank and off-policy policy evaluation.

Related papers

• COD: Learning Conditional Invariant Representation for Domain Adaptation Regression [20.676363400841495]
  Domain Adaptation Regression is developed to generalize label knowledge from a source domain to an unlabeled target domain. Existing conditional distribution alignment theory and methods with discrete prior are no longer applicable. To minimize the discrepancy, a COD-based conditional invariant representation learning model is proposed.
  arXiv  Detail & Related papers  (2024-08-13T05:08:13Z)
• Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift [9.387706860375461]
  A distribution shift occurs when the underlying data-generating process changes, leading to a deviation in the model's performance. The prediction interval serves as a crucial tool for characterizing uncertainties induced by their underlying distribution. We propose methodologies for aggregating prediction intervals to obtain one with minimal width and adequate coverage on the target domain.
  arXiv  Detail & Related papers  (2024-05-16T17:55:42Z)
• Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data [17.991833729722288]
  We propose a novel policy learning algorithm, PESsimistic CAusal Learning (PESCAL) Our key observation is that, by incorporating auxiliary variables that mediate the effect of actions on system dynamics, it is sufficient to learn a lower bound of the mediator distribution function, instead of the Q-function. We provide theoretical guarantees for the algorithms we propose, and demonstrate their efficacy through simulations, as well as real-world experiments utilizing offline datasets from a leading ride-hailing platform.
  arXiv  Detail & Related papers  (2024-03-18T14:51:19Z)
• Bi-Level Offline Policy Optimization with Limited Exploration [1.8130068086063336]
  We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. We propose a bi-level structured policy optimization algorithm that models a hierarchical interaction between the policy (upper-level) and the value function (lower-level) We evaluate our model using a blend of synthetic, benchmark, and real-world datasets for offline RL, showing that it performs competitively with state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-10-10T02:45:50Z)
• Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework [8.572441599469597]
  We study high-confidence off-policy evaluation in the context of infinite-horizon Markov decision processes. The objective is to establish a confidence interval (CI) for the target policy value using only offline data pre-collected from unknown behavior policies. We show that our algorithm is sample-efficient, error-robust, and provably convergent even in non-linear function approximation settings.
  arXiv  Detail & Related papers  (2023-09-23T06:35:44Z)
• A Tale of Sampling and Estimation in Discounted Reinforcement Learning [50.43256303670011]
  We present a minimax lower bound on the discounted mean estimation problem. We show that estimating the mean by directly sampling from the discounted kernel of the Markov process brings compelling statistical properties.
  arXiv  Detail & Related papers  (2023-04-11T09:13:17Z)
• Near-optimal inference in adaptive linear regression [60.08422051718195]
  Even simple methods like least squares can exhibit non-normal behavior when data is collected in an adaptive manner. We propose a family of online debiasing estimators to correct these distributional anomalies in at least squares estimation. We demonstrate the usefulness of our theory via applications to multi-armed bandit, autoregressive time series estimation, and active learning with exploration.
  arXiv  Detail & Related papers  (2021-07-05T21:05:11Z)
• CoinDICE: Off-Policy Confidence Interval Estimation [107.86876722777535]
  We study high-confidence behavior-agnostic off-policy evaluation in reinforcement learning. We show in a variety of benchmarks that the confidence interval estimates are tighter and more accurate than existing methods.
  arXiv  Detail & Related papers  (2020-10-22T12:39:11Z)
• Batch Stationary Distribution Estimation [98.18201132095066]
  We consider the problem of approximating the stationary distribution of an ergodic Markov chain given a set of sampled transitions. We propose a consistent estimator that is based on recovering a correction ratio function over the given data.
  arXiv  Detail & Related papers  (2020-03-02T09:10:01Z)
• Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning [70.01650994156797]
  Off- evaluation of sequential decision policies from observational data is necessary in batch reinforcement learning such as education healthcare. We develop an approach that estimates the bounds of a given policy. We prove convergence to the sharp bounds as we collect more confounded data.
  arXiv  Detail & Related papers  (2020-02-11T16:18:14Z)

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.