Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes

• URL: http://arxiv.org/abs/2404.00099v2
• Date: Fri, 01 Nov 2024 19:00:50 GMT
• Title: Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes
• Authors: Andrew Bennett, Nathan Kallus, Miruna Oprescu, Wen Sun, Kaiwen Wang,
• Abstract summary: We study the evaluation of a policy best-parametric and worst-case perturbations to a decision process (MDP) We use transition observations from the original MDP, whether they are generated under the same or a different policy. Our estimator is also estimated statistical inference using Wald confidence intervals.
• Score: 44.974100402600165
• License:
• Abstract: We study the evaluation of a policy under best- and worst-case perturbations to a Markov decision process (MDP), using transition observations from the original MDP, whether they are generated under the same or a different policy. This is an important problem when there is the possibility of a shift between historical and future environments, $\textit{e.g.}$ due to unmeasured confounding, distributional shift, or an adversarial environment. We propose a perturbation model that allows changes in the transition kernel densities up to a given multiplicative factor or its reciprocal, extending the classic marginal sensitivity model (MSM) for single time-step decision-making to infinite-horizon RL. We characterize the sharp bounds on policy value under this model $\unicode{x2013}$ $\textit{i.e.}$, the tightest possible bounds based on transition observations from the original MDP $\unicode{x2013}$ and we study the estimation of these bounds from such transition observations. We develop an estimator with several important guarantees: it is semiparametrically efficient, and remains so even when certain necessary nuisance functions, such as worst-case Q-functions, are estimated at slow, nonparametric rates. Our estimator is also asymptotically normal, enabling straightforward statistical inference using Wald confidence intervals. Moreover, when certain nuisances are estimated inconsistently, the estimator still provides valid, albeit possibly not sharp, bounds on the policy value. We validate these properties in numerical simulations. The combination of accounting for environment shifts from train to test (robustness), being insensitive to nuisance-function estimation (orthogonality), and addressing the challenge of learning from finite samples (inference) together leads to credible and reliable policy evaluation.

Related papers

• Relaxed Quantile Regression: Prediction Intervals for Asymmetric Noise [51.87307904567702]
  Quantile regression is a leading approach for obtaining such intervals via the empirical estimation of quantiles in the distribution of outputs. We propose Relaxed Quantile Regression (RQR), a direct alternative to quantile regression based interval construction that removes this arbitrary constraint. We demonstrate that this added flexibility results in intervals with an improvement in desirable qualities.
  arXiv  Detail & Related papers  (2024-06-05T13:36:38Z)
• Offline Bayesian Aleatoric and Epistemic Uncertainty Quantification and Posterior Value Optimisation in Finite-State MDPs [3.1139806580181006]
  We address the challenge of quantifying Bayesian uncertainty in offline use cases of finite-state Markov Decision Processes (MDPs) with unknown dynamics. We use standard Bayesian reinforcement learning methods to capture the posterior uncertainty in MDP parameters. We then analytically compute the first two moments of the return distribution across posterior samples and apply the law of total variance. We highlight the real-world impact and computational scalability of our method by applying it to the AI Clinician problem.
  arXiv  Detail & Related papers  (2024-06-04T16:21:14Z)
• Off-Policy Evaluation in Markov Decision Processes under Weak Distributional Overlap [5.0401589279256065]
  We re-visit the task of off-policy evaluation in Markov decision processes (MDPs) under a weaker notion of distributional overlap. We introduce a class of truncated doubly robust (TDR) estimators which we find to perform well in this setting.
  arXiv  Detail & Related papers  (2024-02-13T03:55:56Z)
• 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)
• 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)
• On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks [23.502721524477444]
  We present a synthetic example illustrating how this approach can lead to very poor but stable estimates. We identify the culprit to be the log-likelihood loss, along with certain conditions that exacerbate the issue. We present an alternative formulation, termed $beta$-NLL, in which each data point's contribution to the loss is weighted by the $beta$-exponentiated variance estimate.
  arXiv  Detail & Related papers  (2022-03-17T08:46:17Z)
• 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)
• GenDICE: Generalized Offline Estimation of Stationary Values [108.17309783125398]
  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.
  arXiv  Detail & Related papers  (2020-02-21T00:27:52Z)
• 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.