New methods estimate policy value and gradients for deterministic policies from off-policy data.
problem Estimating policy value and gradients for deterministic policies from off-policy data.
method Proposed new doubly robust estimators based on kernelization approaches.
result Demonstrated a rate independent of horizon length for policy value and gradient estimation.
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…
In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown. Via a series of empirical studies, we demonstrate how accurate OPE is strongly dependent on the calibration of estimated behaviour policy models: how precisely …
The paper explains why estimating a history-dependent policy can reduce MSE in reinforcement learning.
problem Understanding why history-dependent policies can improve MSE in off-policy evaluation.
method The paper derives a bias-variance decomposition of MSE for various OPE estimators, showing how history-dependent policies can decrease variance and increase bias.
result History-dependent policies can decrease the variance of importance sampling estimators, leading to lower MSE.
New method improves off-policy critic evaluation in reinforcement learning.
problem High variance and instability in off-policy policy evaluation.
method Doubly robust estimators applied to actor-critic algorithms.
result Doubly robust estimation significantly improves performance in continuous control tasks.
A new estimator for evaluating policies in unknown environments.
problem Evaluating policies when both logging policy and value function are unknown.
method Doubly-Robust (DR) off-policy evaluation (OPE) estimator, DRUnknown, that estimates both the logging policy and value function.
result DRUnknown achieves the smallest asymptotic variance and is optimal when both models are correctly specified.
Paper proposes FPG algorithm for unbiased off-policy PG estimation.
problem Challenges in off-policy policy gradient estimation.
method Double Fitted PG estimation (FPG) algorithm for arbitrary policy parameterization.
result Empirically, FPG significantly outperforms existing methods.
Paper tackles efficient policy gradient estimation from off-policy data.
problem Estimating policy gradients from off-policy data is challenging and inefficient.
method Derives asymptotic lower bounds, proposes a meta-algorithm with 3-way robustness, and establishes convergence guarantees.
result Meta-algorithm achieves the lower bound on mean-squared error without parametric assumptions.
A new estimator improves off-policy evaluation in RL, outperforming existing methods.
problem Estimating performance of a new policy using historical data from a different policy.
method Doubly-robust estimator based on Targeted Maximum Likelihood Estimation, with variance reduction techniques.
result Our estimator uniformly outperforms existing methods across various RL environments and levels of model misspecification.
ScoreMatchingRiesz improves debiased machine learning and policy effects estimation.
problem Improving debiased machine learning and policy effects estimation.
method Score matching and Riesz representer estimation.
result Estimates policy path for continuous treatments, improving interpretability.
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.
OPERA blends multiple OPE estimators to evaluate new policies offline.
problem Lack of reliable offline policy evaluation methods for new policies.
method Adaptive blending of multiple OPE estimators without explicit selection.
result Consistent and reliable policy evaluation framework for offline RL.
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 …
Study proposes new OPE estimators for two-player zero-sum games.
problem Evaluating new policies using historical data from a different policy in multi-player zero-sum games.
method Doubly robust and double reinforcement learning estimators to project exploitability.
result Prove exploitability estimation error bounds and regret bounds for policy profiles.
DBQPG improves policy gradient estimation with fewer samples.
problem Accurate policy gradient estimation with limited samples.
method Deep Bayesian Quadrature Policy Gradient (DBQPG).
result DBQPG provides more accurate and less variable gradient estimates.
Due to the high variance of policy gradients, on-policy optimization algorithms are plagued with low sample efficiency. In this work, we propose Augment-Reinforce-Merge (ARM) policy gradient estimator as an unbiased low-variance alternative to previous baseline estimators on tasks with binary action space, inspired by …
Faster policy learning via continuous-time gradients.
problem Efficiently estimating policy gradients for continuous-time systems.
method Approximating continuous-time gradients directly, using adaptive discretization.
result More efficient policy gradient estimator leads to faster learning.
Pessimistic estimator improves multi-objective policy optimization.
problem Optimizing multi-objective policies from existing data.
method Pessimistic estimator based on inverse propensity scores (IPS).
result Pessimistic estimator outperforms naive IPS estimator in theory and experiments.
Paper tackles RL with continuous actions and unmeasured confounders.
problem Offline policy learning with continuous actions and unmeasured confounders.
method Developed a novel identification result and a minimax estimator for nonparametric policy value estimation.
result Introduced a policy-gradient-based algorithm to identify the optimal policy.
Many continuous control tasks have bounded action spaces. When policy gradient methods are applied to such tasks, out-of-bound actions need to be clipped before execution, while policies are usually optimized as if the actions are not clipped. We propose a policy gradient estimator that exploits the knowledge of action…
Study minimax off-policy evaluation in multi-armed bandits with known and unknown behavior policies.
problem Evaluate policies in multi-armed bandits with unknown behavior policies.
method Develop minimax rate-optimal procedures for known and unknown behavior policies, including the Switch estimator and Chebyshev polynomial-based estimator.
result Plug-in estimator achieves optimal competitive ratio up to a logarithmic factor when behavior policy is unknown.
Study efficient policy value estimation with sublinear samples.
problem Estimating optimal policy value in stochastic disjoint linear bandits.
method Sublinear sample estimation of optimal policy value.
result Achieves near optimal estimation error with sublinear samples.
End-to-end policy learning method improves CATE estimation.
problem Learning optimal treatment policies from partially observed data.
method Modified causal forest for policy learning.
result Maximizing policy value is equivalent to minimizing CATE.
Randomized trials, also known as A/B tests, are used to select between two policies: a control and a treatment. Given a corresponding set of features, we can ideally learn an optimized policy P that maps the A/B test data features to action space and optimizes reward. However, although A/B testing provides an unbiased …
Estimates and infers multi-stage stationary treatment policies with variable selection.
problem Valid inference for multi-stage stationary treatment policies with high-dimensional feature variables.
method Estimate the value function using augmented inverse probability weighted estimator, apply penalty for variable selection, construct one-step improvements for valid inference.
result Improved estimators are asymptotically normal, valid inference for policy parameters demonstrated.
A new framework estimates policy value robustly against confounders.
problem Estimating policy value in the presence of unobserved confounders.
method Convex programming for sharp lower bounds.
result Sharp lower bounds on policy value for robust inference.
New findings show optimization is crucial for OPL in large action spaces.
problem Challenges in optimizing policies for large action spaces in offline contextual bandits.
method Weighed log-likelihood objectives and estimator-aware policy parametrization.
result Simple weighted log-likelihood objectives enjoy better optimization properties and recover competitive policies.
The paper introduces a novel method for stable off-policy learning using value function chaining.
problem Stability issues in off-policy reinforcement learning.
method The approach involves learning on-policy first, then chaining off-policy value estimates.
result The method guarantees convergence and can approximate off-policy TD solutions.
This work improves policy evaluation and selection using logarithmic smoothing for pessimistic off-policy estimation.
problem Offline evaluation and selection of policies from past data.
method Develops novel concentration bounds and a logarithmically smoothed estimator (LS) for improved policy selection and learning.
result The logarithmically smoothed estimator (LS) provides tighter bounds and better policy selection and learning.
Combines multiple OPE estimators into a more accurate and efficient estimate.
problem Offline evaluation of recommender systems using biased data.
method Meta-analysis of correlated OPE estimators, accounting for inter-estimator correlation.
result Improved statistical efficiency and accuracy in estimating 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.
We propose an estimator and confidence interval for computing the value of a policy from off-policy data in the contextual bandit setting. To this end we apply empirical likelihood techniques to formulate our estimator and confidence interval as simple convex optimization problems. Using the lower bound of our confiden…
Study optimal treatment assignment policies under strategic agent responses.
problem Learning optimal treatment policies with strategic agents complicates estimation.
method Dynamic model with threshold convergence to mean-field equilibrium, consistent estimator for policy gradient.
result Threshold for treatment assignment converges to mean-field equilibrium threshold under large but finite number of agents.
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.
The paper tackles batch policy learning in Markov Decision Processes, focusing on average reward maximization.
problem Maximizing long-term average reward in Markov Decision Processes with batch learning.
method Doubly robust estimator for average reward, optimization algorithm for optimal policy, finite-sample regret guarantee.
result The proposed method achieves semiparametric efficiency and provides a finite-sample regret guarantee.
CoinDICE estimates confidence intervals for unknown behavior policies in reinforcement learning.
problem Estimating value of a target policy using only behavior policy data.
method Function space embedding, generalized empirical likelihood method, Lagrangian optimization.
result Valid confidence intervals with tighter and more accurate estimates than existing methods.
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.
Develops a method to estimate optimal policy value in online learning.
problem Challenges in evaluating ongoing policies in online learning environments.
method Doubly Robust Interval Estimation (DREAM) method.
result Valid inference on online conditional mean estimator with asymptotically normal distribution.
Efficient policy learning from observational data using weighted classification reductions.
problem Efficient policy evaluation does not necessarily lead to efficient estimation of policy parameters.
method Proposed an estimation approach based on generalized method of moments, efficient for policy parameters.
result Demonstrated empirical efficiency and regret benefits of a proposed method.
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.
Develops methods to estimate and quantify uncertainty in off-policy evaluation.
problem Uncertainty quantification in off-policy evaluation for new policy deployment.
method Designs a pseudo policy to generate subsamples and applies conformal prediction.
result Valid interval estimators for target policy's return with uncertainty quantification.
Paper finds efficient OPE estimator for multiple logging policies with minimum variance.
problem Finding optimal importance sampling weights for multiple logging policies with varying variances.
method Established efficiency bound under stratified sampling and proposed an estimator achieving this bound.
result Proposed estimator achieves minimum variance for any instance.
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 paper investigates methods for estimating the optimal stochastic control policy for a Markov Decision Process with unknown transition dynamics and an unknown reward function. This form of model-free reinforcement learning comprises many real world systems such as playing video games, simulated control tasks, and r…
The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in this scenario is how to reduce the variance of policy gradient estimates for reliable policy updates. In this paper, we combine the followi…
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. New method learns optimal policies in presence of unmeasured confounders.
problem Optimal policy learning with unobserved confounders.
method Causal-assisted policy learning methods using instrumental variables and negative controls.
result Policies are ildeO(n−1/2) quantile-optimal under mild coverage assumptions. 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.