A generalization error for Q-learning
From MaRDI portal
Recommendations
- Error bounds for constant step-size \(Q\)-learning
- \({\mathcal Q}\)-learning
- Q-Learning with Linear Function Approximation
- Approximate Q Learning for Controlled Diffusion Processes and Its Near Optimality
- Learning Near-Optimal Policies with Bellman-Residual Minimization Based Fitted Policy Iteration and a Single Sample Path
Cited in
(73)- Algebraic results and bottom-up algorithm for policies generalization in reinforcement learning using concept lattices
- Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path
- A single-index model with multiple-links
- Sequential multiple assignment randomized trial (SMART) with adaptive randomization for quality improvement in depression treatment program
- Sequential advantage selection for optimal treatment regime
- D-learning to estimate optimal individual treatment rules
- High-dimensional inference for personalized treatment decision
- Data-driven approximate Q-learning stabilization with optimality error bound analysis
- Error bounds for constant step-size \(Q\)-learning
- Generalization error bounds of dynamic treatment regimes in penalized regression-based learning
- Estimating optimal shared-parameter dynamic regimens with application to a multistage depression clinical trial
- Q-learning for estimating optimal dynamic treatment rules from observational data
- Inference for optimal dynamic treatment regimes using an adaptive m-out-of-n bootstrap scheme
- Reinforcement learning strategies for clinical trials in nonsmall cell lung cancer
- Towards min max generalization in reinforcement learning
- scientific article; zbMATH DE number 5957196 (Why is no real title available?)
- Incorporating patient preferences into estimation of optimal individualized treatment rules
- scientific article; zbMATH DE number 5957431 (Why is no real title available?)
- Dynamic treatment regimes: technical challenges and applications
- Q-learning with censored data
- Quantile-optimal treatment regimes
- A Bayesian machine learning approach for optimizing dynamic treatment regimes
- Estimation for optimal treatment regimes with survival data under semiparametric model
- \(i\)Fusion: individualized fusion learning
- Multi-Armed Angle-Based Direct Learning for Estimating Optimal Individualized Treatment Rules With Various Outcomes
- Estimating dynamic treatment regimes in mobile health using V-learning
- A Sequential Significance Test for Treatment by Covariate Interactions
- Estimation and optimization of composite outcomes
- Estimation of individualized decision rules based on an optimized covariate-dependent equivalent of random outcomes
- The QLBS Q-Learner goes NuQLear: fitted Q iteration, inverse RL, and option portfolios
- Performance guarantees for individualized treatment rules
- Learning when-to-treat policies
- Stochastic tree search for estimating optimal dynamic treatment regimes
- High-Dimensional Precision Medicine From Patient-Derived Xenografts
- Resampling‐based confidence intervals for model‐free robust inference on optimal treatment regimes
- A constrained single‐index regression for estimating interactions between a treatment and covariates
- On Robustness of Individualized Decision Rules
- Functional additive models for optimizing individualized treatment rules
- Optimal Treatment Regimes: A Review and Empirical Comparison
- Transformation-Invariant Learning of Optimal Individualized Decision Rules with Time-to-Event Outcomes
- Target Network and Truncation Overcome the Deadly Triad in \(\boldsymbol{Q}\)-Learning
- Evaluating the use of generalized dynamic weighted ordinary least squares for individualized HIV treatment strategies
- Transfer Learning of Individualized Treatment Rules from Experimental to Real-World Data
- Off-policy evaluation in partially observed Markov decision processes under sequential ignorability
- Learning Non-monotone Optimal Individualized Treatment Regimes
- A single index model for longitudinal outcomes to optimize individual treatment decision rules
- Penalized robust learning for optimal treatment regimes with heterogeneous individualized treatment effects
- On ``Reflections on the concept of optimality of single decision point treatment regimes
- Robust regression for optimal individualized treatment rules
- Doubly robust estimation of optimal dynamic treatment regimes with multicategory treatments and survival outcomes
- Ascertaining properties of weighting in the estimation of optimal treatment regimes under monotone missingness
- Accommodating misclassification effects on optimizing dynamic treatment regimes with Q-learning
- A high-dimensional single-index regression for interactions between treatment and covariates
- Deep spatial Q-learning for infectious disease control
- Estimating the optimal individualized treatment regime based on semiparametric model with Bernstein polynomials
- Transfer Q-learning for finite-horizon Markov decision processes
- Reinforcement learning in modern biostatistics: constructing optimal adaptive interventions
- Asymptotic inference for multi-stage stationary treatment policy with variable selection
- Optimization of multi-stage dynamic treatment regimes utilizing accumulated data
- A robust covariate-balancing method for learning optimal individualized treatment regimes
- Estimation of optimal dynamic treatment assignment rules under policy constraints
- Estimating optimal treatment regimes via subgroup identification in randomized control trials and observational studies
- Federated learning of robust individualized decision rules with application to heterogeneous multihospital sepsis population
- Total stability of outcome weighted learning
- Q-learning residual analysis: application to the effectiveness of sequences of antipsychotic medications for patients with schizophrenia
- Estimating expectile-optimal treatment regimes
- Using pilot data to size a two-arm randomized trial to find a nearly optimal personalized treatment strategy
- Deep approximate policy iteration
- Smoothed estimation on optimal treatment regime under semisupervised setting in randomized trials
- Online outcome weighted learning with general loss functions
- Data-Driven Knowledge Transfer in Batch Q * Learning
- Medical knowledge integration into reinforcement learning algorithms for dynamic treatment regimes
- Reluctant transfer learning in penalized regressions for individualized treatment rules under effect heterogeneity
This page was built for publication: A generalization error for Q-learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3093292)
