Paper addresses off-policy evaluation and learning with covariate shift.
problem Evaluating and training a new policy using historical data with a covariate shift.
method Derives efficiency bounds and proposes doubly robust estimators for OPE and OPL under covariate shift.
result Proposes estimators for off-policy evaluation and learning under covariate shift.
Paper improves bootstrapping for off-policy reinforcement learning inference.
problem Improving bootstrapping for off-policy reinforcement learning inference.
method Proposes a bootstrapping FQE method for off-policy statistical inference and a subsampling procedure to improve runtime.
result Asymptotically efficient and distributionally consistent bootstrapping FQE method for off-policy inference.
Improved off-policy evaluation for MDPs with weak distributional overlap.
problem Evaluation of policies when target and data-collection distributions are not strongly overlapping.
method Truncated Doubly Robust (TDR) estimators for off-policy evaluation in MDPs under weak distributional overlap.
result TDR estimators can recover large-sample behavior and are consistent even when distribution ratios are not square-integrable.
New method extends fitted Q-evaluation for distributional off-policy reinforcement learning.
problem Estimating return distribution in reinforcement learning using offline data.
method Developed a set of guiding principles and new FDE methods with theoretical justification.
result FDE methods outperform existing approaches in simulations and real-world games.
We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the distribution of states visited under the behavior policy used to collect data, and what …
Unified DICE estimators as regularized Lagrangians for improved off-policy evaluation.
problem Improving off-policy evaluation from behavior-agnostic data.
method Unified derivation of DICE estimators as regularized Lagrangians of a linear program.
result Dual solutions offer greater flexibility and provide superior estimates in practice.
Estimation of importance sampling weights for off-policy evaluation of contextual bandits often results in imbalance - a mismatch between the desired and the actual distribution of state-action pairs after weighting. In this work we present balanced off-policy evaluation (B-OPE), a generic method for estimating weights…
New method for distributional off-policy evaluation using Bellman residual minimization.
problem Learning return distribution from offline data generated by a different policy.
method Energy Bellman Residual Minimizer (EBRM) method.
result Established finite-sample error bound for EBRM estimator.
Paper introduces DQPOPE for estimating return distributions in reinforcement learning.
problem Estimating the entire return distribution from off-policy data.
method Deep quantile process regression for distributional off-policy evaluation.
result DQPOPE achieves statistical advantages by estimating full return distribution with same sample size.
We study the problem of off-policy evaluation (OPE) in Reinforcement Learning (RL), where the aim is to estimate the performance of a new policy given historical data that may have been generated by a different policy, or policies. In particular, we introduce a novel doubly-robust estimator for the OPE problem in RL, b…
This paper extends off-policy reinforcement learning to the multi-agent case in which a set of networked agents communicating with their neighbors according to a time-varying graph collaboratively evaluates and improves a target policy while following a distinct behavior policy. To this end, the paper develops a multi-…
We consider off-policy policy evaluation when the trajectory data are generated by multiple behavior policies. Recent work has shown the key role played by the state or state-action stationary distribution corrections in the infinite horizon context for off-policy policy evaluation. We propose estimated mixture policy …
This paper optimizes off-policy evaluation in reinforcement learning with function approximation.
problem Estimating cumulative value of a new policy from logged data generated by an unknown policy.
method Regression-based fitted Q iteration method, equivalent to estimating conditional mean embedding of transition operator.
result The method is minimax-optimal, with nearly minimal estimation error.
Novel LSE estimator improves off-policy learning and evaluation.
problem High variance and poor performance with low-quality propensity scores and heavy-tailed reward distributions.
method Introduces a novel estimator based on the log-sum-exponential (LSE) operator.
result Achieves convergence rate of O(n−ε/(1+ε)) for regret bounds. Paper proposes a framework for reliable off-policy evaluation in reinforcement learning.
problem Quantifying uncertainty in off-policy estimates for safe deployment of target policies.
method Distributionally robust optimization for creating confidence bounds.
result Non-asymptotic and asymptotic guarantees for robust cumulative reward estimates.
This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large errors. We define the problem of off-policy evaluation for Partially Observable Mark…
Bayesian approach for modeling counterfactual distribution and off-policy evaluation.
problem Modeling the counterfactual distribution and off-policy evaluation.
method Bayesian conditional mean embeddings and novel Bayesian methods for estimating ultimate treatment effect.
result Quantifying epistemic uncertainty in the counterfactual distribution and off-policy evaluation.
FQE with deep neural networks achieves asymptotic normality and finite-sample bounds.
problem Theoretical understanding of FQE with general differentiable function approximators.
method Z-estimation theory applied to FQE with deep neural networks.
result FQE estimation error is asymptotically normal with explicit variance.
Study tackles OPE in confounded settings, estimating policy value from proxies.
problem Difficulty in OPE due to unobserved confounders in infinite-horizon RL.
method Two-stage approach: estimating stationary distribution ratios and combining optimal balancing.
result Policy value can be identified from off-policy data with proxies and latent variable model.
This work provides guarantees for off-policy function estimation under realizability assumptions.
problem Estimating the value function of a policy under user-specified error-measuring distributions.
method The approach involves imposing a flexible regularization on the MIS objectives to account for an arbitrary user-specified distribution.
result Exact characterization of the optimal dual solution that determines the data-coverage assumption in the case of value-function learning.
Study improves off-policy evaluation from non-i.i.d. bandit samples.
problem Improving off-policy evaluation from non-independent bandit samples.
method Constructing an estimator from a standardized martingale difference sequence.
result Proposed estimator performs better than existing methods.
Unified framework for error quantification in off-policy evaluation with distributional shift.
problem Establishing high-confidence CI for target policy value from offline data.
method Unified error analysis quantifying misspecification and sampling errors.
result Achieves tightest possible CI and robustness against distributional shifts.
New methods improve robust decision-making under uncertainty in off-policy evaluation.
problem Statistical uncertainty and causal considerations in off-policy evaluation.
method Marginal Ratio (MR) estimator, Conformal Off-Policy Prediction (COPP), causal bounds.
result Improved robustness and uncertainty quantification in off-policy decision-making.
This paper improves sample efficiency for off-policy evaluation with preference data.
problem Improving sample efficiency for off-policy evaluation with preference data.
method Using a deep neural network to learn the value function and leveraging manifold structure.
result Established a provably efficient guarantee for off-policy evaluation with RLHF.
This paper proposes a method to evaluate policies using quantile metrics, improving upon existing mean-based approaches.
problem Evaluating policies using mean-based metrics ignores the variability of outcomes, especially in skewed reward distributions.
method The paper introduces a doubly-robust inference procedure for quantile off-policy evaluation using deep conditional generative learning.
result The proposed estimator outperforms classical OPE estimators for mean outcomes in heavy-tailed reward distributions.
New method stabilizes FQE by reweighting Bellman targets.
problem Stability guarantees for FQE often rely on Bellman completeness, which can fail with function approximation.
method Proposes stationary-weighted FQE, reweighting Bellman targets by stationary target-to-behavior density ratio.
result Proves finite-sample linear convergence to stationary projected Bellman fixed point without Bellman completeness.
We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new policy after every policy gradient update. Despite enormous success of off-policy …
New methods for anytime-valid off-policy inference in contextual bandits.
problem Estimating properties of hypothetical policies in adaptive experiments.
method Modern martingale techniques for comprehensive OPE inference.
result Valid anytime inference for off-policy mean reward values and entire reward distributions.
Paper addresses OPE for dependent bandit samples using MDS and batch updates.
problem Evaluating policies from non-i.i.d. historical data in contextual bandits.
method Constructs an MDS-based estimator for dependent samples, solves batch update and deficient support issues.
result Derives an asymptotically normal estimator for evaluation policy value.
Method selects best estimator for off-policy evaluation.
problem Choosing the best estimator for off-policy evaluation.
method Generic data-driven method for estimator selection.
result Method is competitive with oracle estimator, up to a constant factor.
This paper studies optimal approximation factors in misspecified off-policy RL, identifying key factors under various settings.
problem Understanding optimal approximation factors in misspecified off-policy value function estimation.
method Examined various settings including weighted L2-norm, L∞ norm, state aliasing, and state coverage. result Established optimal asymptotic approximation factors for different norms and identified two instance-dependent factors for L2(μ) norm. OSIRIS reduces variance in off-policy evaluation by omitting irrelevant states.
problem High variance in importance sampling-based OPE estimators.
method OSIRIS reduces variance by omitting likelihood ratios associated with states irrelevant to return.
result OSIRIS is unbiased and has lower variance than ordinary importance sampling.
Study designs logging policies to minimize off-policy evaluation error.
problem Minimizing OPE error with logging policies for target policies.
method Characterizes reward-coverage tradeoff, proposes a unifying framework, derives optimal policies.
result Provides actionable guidance for firms choosing recommendation systems.
New method estimates off-policy data without needing known behavior policy.
problem Long-horizon reinforcement learning with limited on-policy data.
method Formulates problem as fixed point of operator, uses RKHS for estimation.
result Asymptotic consistency and finite-sample generalization proven.
New estimator uses clustering to improve off-policy evaluation accuracy.
problem Improving off-policy evaluation accuracy when logging and evaluation policies differ.
method Proposes an estimator that shares information across similar contexts using clustering.
result Clustering contexts improves estimation accuracy, especially in deficient information settings.
VA-OPE improves OPE by incorporating variance information, achieving tighter error bounds.
problem Estimating value function of a target policy from offline data collected by a behavior policy.
method Proposes VA-OPE, an algorithm that reweights Bellman residual using estimated variance of the value function.
result Achieves a tighter error bound than the best-known result.
New algorithms improve policy evaluation in reinforcement learning.
problem Off-policy stability and on-policy efficiency issues in policy evaluation.
method Introduced novel algorithms using oblique projection method.
result Demonstrated both off-policy stability and on-policy efficiency.
New method for evaluating policies in complex decision-making models with hidden variables.
problem Evaluating policies in partially observable Markov decision processes with hidden confounders.
method Introduces novel identification methods and minimax estimation techniques for linking target policy's value and observed data distribution.
result Proposes three estimators for off-policy evaluation in POMDPs with latent confounders, demonstrating their effectiveness through nonasymptotic and asymptotic analysis.
The paper improves QD policy ensembles using distribution ratio estimators.
problem Training diverse and high-quality reinforcement learning agents.
method Using Stein variational gradient descent and distribution ratio estimators.
result The method generates diverse and high-quality reinforcement learning agents.
This paper reviews off-policy evaluation methods in reinforcement learning.
problem Efficiency and accuracy of off-policy evaluation methods in reinforcement learning.
method Discussion of existing OPE methods, their statistical properties, and related research directions.
result Efficiency bounds and state-of-the-art OPE methods in reinforcement learning.
Develops confidence bounds for off-policy evaluation in contextual bandits.
problem Evaluating policies that were not used to collect data.
method Martingale analysis for non-asymptotic, non-parametric, and valid confidence sequences.
result Empirically tight bounds on failure probability and width.
New estimator reduces variance in off-policy evaluation for contextual bandits.
problem High variance in current OPE methods for contextual bandits.
method Marginal Density Ratio (MR) estimator focusing on marginal distribution shift.
result MR estimator reduces variance compared to IPW and DR methods.
DOLCE improves off-policy evaluation and learning by decomposing effects.
problem Bias in off-policy evaluation and learning due to policy mismatch.
method Uses lagged contexts and a moment-based training procedure to decompose and cancel bias.
result DOLCE achieves substantial improvements in off-policy evaluation and learning.
We consider the problem of off-policy evaluation in Markov decision processes. Off-policy evaluation is the task of evaluating the expected return of one policy with data generated by a different, behavior policy. Importance sampling is a technique for off-policy evaluation that re-weights off-policy returns to account…
STAR framework reduces OPE variance by distilling complex problems into discrete ARPs.
problem High variance and bias in off-policy evaluation methods.
method STAR framework that includes various OPE estimators and leverages state abstraction.
result Predictions from ARPs estimated from off-policy data are asymptotically correct.
Off-policy deep reinforcement learning (RL) algorithms are incapable of learning solely from batch offline data without online interactions with the environment, due to the phenomenon known as \textit{extrapolation error}. This is often due to past data available in the replay buffer that may be quite different from th…
Paper proposes a method to create more reliable confidence intervals for off-policy evaluations.
problem Creating reliable confidence intervals for off-policy evaluations.
method Proposes a deeply-debiasing procedure to construct efficient, robust, and flexible confidence intervals.
result Validated by theoretical results and numerical experiments, the method improves the reliability of off-policy evaluations.
Unified coverage analysis for linear off-policy evaluation in reinforcement learning.
problem Lack of a unified understanding of coverage parameters in linear off-policy evaluation.
method Developed a novel finite-sample analysis for LSTDQ algorithm, introducing feature-dynamics coverage.
result Unified understanding of coverage parameters in linear off-policy evaluation.