Extends double linear policy with time-varying weights and proves robust positive expectation.
problem Ensuring robustness in policy optimization with time-varying parameters.
method Employed a novel elementary symmetric polynomials characterization approach to prove robust positive expectation (RPE). Derived explicit expressions for expected cumulative gain-loss and variance.
result Proved the robust positive expectation property holds for the extended double linear policy.
A new approach optimizes weights in DLP for better risk-adjusted performance.
problem Optimizing time-varying weights in Double Linear Policy (DLP) for better risk-adjusted performance.
method Stochastic Model Predictive Control (SMPC) framework to maximize risk-adjusted returns while enforcing constraints.
result Empirical results show improved risk-adjusted performance and drawdown control.
New trading policies preserve robust gains in presence of transaction costs.
problem Maintaining robust gains in asset trading with transaction costs.
method Proposed double linear trading policies, analyzed with Monte Carlo simulations and historical data.
result Desired robust positive expected gain can be preserved under certain conditions.
Double Q-learning has the same mean-squared error as Q-learning under certain conditions.
problem Comparing the mean-squared error of Double Q-learning and Q-learning.
method Theoretical analysis based on Lyapunov equations for both tabular and linear function approximation settings.
result The asymptotic mean-squared error of Double Q-learning is exactly equal to that of Q-learning under specific conditions.
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.
DML-IV improves IV regression for learning decision policies by reducing bias.
problem Spurious correlations in offline datasets caused by hidden confounders.
method Double/debiased machine learning (DML) framework to reduce bias in two-stage IV regression.
result DML-IV outperforms state-of-the-art methods and learns high-performing policies.
FLAP adapts policies quickly to new tasks using shared linear representations.
problem Adapting policies to new tasks efficiently and effectively.
method FLAP uses a shared linear representation and a separate adapter network for quick adaptation.
result FLAP achieves up to 8X faster adaptation and significantly better performance on out-of-distribution tasks.
Double descent found in DRL, improving generalization with model capacity.
problem Generalization in over-parameterized DRL models.
method Actor-Critic framework, Policy Entropy metric.
result Policy Entropy significantly reduces as model capacity increases, indicating improved generalization.
New algorithm reduces switching costs in RL beyond linear MDPs.
problem Costly policy switching in reinforcement learning.
method ELEANOR-LowSwitching algorithm for linear Bellman-complete MDPs.
result Achieves near-optimal regret with logarithmic switching cost.
Bayesian design improves by reducing policy training cost.
problem Double intractability in expected information gain limits policy learning.
method Score matching to isolate EIG, then train policy singly intractably.
result Reduced computational burden for policy training, allowing multiple iterations.
Paper proposes adaptive control for unknown systems using reinforcement learning.
problem Adaptive control for unknown, linearizable systems.
method On-policy reinforcement learning for discrete-time, stochastic systems.
result Stability and tracking errors concentrate near zero with high probability.
Two new algorithms improve Q* approximation in batch RL with linear error propagation.
problem Improving Q* approximation in batch reinforcement learning.
method Two novel algorithms that estimate Bellman error directly, without quadratic dependence.
result Linear-in-horizon error propagation for batch RL algorithms.
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.
Study uses ML to analyze how interest rates affect fund returns, finding gradient boosting is effective.
problem Understanding how interest rate changes impact fund returns.
method Combines Machine Learning and causal inference, using Double Machine Learning framework.
result Gradient boosting is useful for predicting fund returns, showing a significant negative effect of interest rate increases.
Research provides explicit NPV expressions for double barrier strategies.
problem Calculating expected NPVs of double barrier strategies for regular diffusions.
method Explicit expression using bivariate q-scale function with perturbation technique.
result Explicit expressions for expected NPVs are derived for certain cases.
Proposes fair and robust methods for estimating treatment effects.
problem Estimating treatment effects while maintaining fairness.
method Simple, nonparametric framework with fairness constraints.
result Estimators are double robust and characterize welfare trade-offs.
Method estimates dynamic treatment effects using machine learning and g-estimation.
problem Estimating treatment effects over time with multiple treatments and potential future outcomes.
method Double/debiased machine learning framework for dynamic treatment effects, extending Neyman orthogonal cross-fitted g-estimation. result Provides finite sample guarantees and allows for non-linear effect heterogeneity and high-dimensional parameterizations.
New rule reduces exploration regret to logarithmic, improving bad episode handling.
problem Improving exploration regret in average reward MDPs.
method Replacing Doubling Trick with Vanishing Multiplicative rule in EVI-based algorithms.
result Regret is logarithmic under the new rule, significantly better than linear.
A new algorithm improves offline reinforcement learning robustness.
problem Finding optimal policies in perturbed environments from offline data.
method Doubly Pessimistic Model-based Policy Optimization (P^2MPO) framework.
result Proves sample efficiency with robust partial coverage data.
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.
Automatic debiasing for causal and policy effects using Neural Nets and Random Forests.
problem Estimating causal and policy effects from high-dimensional or non-parametric regression functions.
method Automatic learning of Riesz representation using Neural Nets and Random Forests.
result Automatic debiasing method performs well compared to state-of-the-art algorithms.
We reformulate the option framework as two parallel augmented MDPs. Under this novel formulation, all policy optimization algorithms can be used off the shelf to learn intra-option policies, option termination conditions, and a master policy over options. We apply an actor-critic algorithm on each augmented MDP, yieldi…
This paper explains double descent in linear neural networks, identifying new factors.
problem Understanding double descent in linear neural networks.
method Gradient flow derivation and necessary conditions for double descent.
result Singular values of input-output covariance matrix are important for double descent in two-layer models.
Proposes a new policy gradient algorithm to improve reinforcement learning efficiency and stability.
problem Inefficiency and instability of DDPG in practical applications, and difficulty in controlling Q estimation bias and variance.
method Introduces a Regularly Updated Deterministic (RUD) policy gradient algorithm.
result The RUD algorithm makes better use of new data and has lower Q value variance, leading to improved performance.
Unified minimax value interval for off-policy evaluation and optimization.
problem Overcoming the exponential variance in off-policy evaluation and policy optimization.
method Unified minimax value interval using marginalized importance weights.
result Unified value interval with double robustness, valid when either value-function or importance-weight class is well specified.
Double descent phenomenon explained in simple terms.
problem Understanding the surprising drop in test error in overparameterized models.
method Informal explanation using linear algebra and probability, visual intuition with polynomial regression, mathematical analysis with ordinary linear regression.
result Three factors create double descent: data undersampling, model size, and parameter count. Ablating any one of these factors prevents double descent.
Off-policy evaluation (OPE) in reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. We consider for the first time the semiparametric efficiency limits of OPE in Markov decision processes (MDPs), where actions, rewar…
Study shows double descent curve in high-dimensional linear regression with random projections.
problem Understanding the generalization performance in high-dimensional settings with random projections.
method Fixed prediction problem, ridge regression estimator, minimum norm least-squares fit, random matrix theory, asymptotic equivalents.
result Exhibit a double descent curve for high-dimensional linear regression with random projections.
Paper optimizes financial trading strategies under uncertain market conditions.
problem Guaranteeing robust positive expected profits in financial systems.
method Transformed semi-infinite constraints into structured policies and proposed a novel graphical approach.
result Demonstrated superior risk-adjusted returns and downside risk compared to conventional strategies.
New methods improve off-policy evaluation for survival outcomes with censoring.
problem Systematic underestimation of policy performance due to censoring bias in survival outcomes.
method Proposes IPCW-IPS and IPCW-DR to handle censoring bias in survival outcomes.
result The proposed methods are unbiased and achieve double robustness.
New algorithm reduces reinforcement learning regret to sqrt(T) without strong dynamics assumptions.
problem Infinite-horizon average-reward reinforcement learning with linear MDPs.
method Approximate by discounted-reward MDPs and apply optimistic value iteration.
result Achieves O(sqrt(T)) regret with polynomial complexity.
Off-policy evaluation (OPE) in reinforcement learning is notoriously difficult in long- and infinite-horizon settings due to diminishing overlap between behavior and target policies. In this paper, we study the role of Markovian and time-invariant structure in efficient OPE. We first derive the efficiency bounds for OP…
New method improves regression estimates, reducing bias.
problem Omitted variable bias in high-dimensional linear regression.
method Post-Double-Autometrics, an alternative to Post-Double-Lasso.
result Post-Double-Autometrics outperforms Post-Double-Lasso.
Paper proposes a new method for demand forecasting in pricing contexts.
problem Demand forecasting in pricing contexts, especially in a profit optimal manner.
method Combines Double Machine Learning for causal inference and transformer-based forecasting models.
result Our method outperforms other forecasting methods in off-policy settings.
We construct closed embedded minimal surfaces in the round three-sphere, resembling two parallel copies of the equatorial two-sphere, joined by small catenoidal bridges symmetrically arranged either along two parallel circles of the equator, or along the equatorial circle and the poles. To carry out these constructions…
We develop methods to approximate derivatives for causal inference problems using data.
problem Estimating causal effects from data when distributions are not known.
method Constructive algorithm approximating Gateaux derivatives via finite differencing.
result Derives conditions for finite-difference approximations to preserve statistical benefits.
DFL framework improves action and outcome fairness in policy learning.
problem Fairness in policy learning, especially action and outcome fairness.
method Integrates action and outcome fairness into a multi-objective optimization problem using a lexicographic weighted Tchebyshev method.
result DFL framework improves both action and outcome fairness with minimal value reduction.
Many real world tasks require multiple agents to work together. Multi-agent reinforcement learning (RL) methods have been proposed in recent years to solve these tasks, but current methods often fail to efficiently learn policies. We thus investigate the presence of a common weakness in single-agent RL, namely value fu…
The paper uses machine learning to optimize rework policies in semiconductor manufacturing.
problem Optimizing rework steps to increase yield without increasing costs.
method Applied double/debiased machine learning (DML) to estimate treatment effects.
result Derived optimal rework policies and estimated their value empirically.
Despite the success of single-agent reinforcement learning, multi-agent reinforcement learning (MARL) remains challenging due to complex interactions between agents. Motivated by decentralized applications such as sensor networks, swarm robotics, and power grids, we study policy evaluation in MARL, where agents with jo…
Geometric arguments show simplicial arrangements with few double points can't have an irreducible cubic curve dual.
problem Classifying simplicial arrangements with a linear bound on double points.
method Geometric arguments and structure theorem from Green and Tao.
result Simplicial arrangements with few double points can't have an irreducible cubic curve dual.
Optimal regularization can prevent the double descent phenomenon in learning models.
problem The double descent phenomenon in learning models, where test performance is non-monotonic in sample size and model size.
method Theoretical and empirical study of optimal ℓ2 regularization for linear regression models and neural networks. result Optimally-tuned ℓ2 regularization achieves monotonic test performance for certain models and mitigates the double descent phenomenon for more general models. Paper tackles efficient evaluation of natural stochastic policies in offline RL.
problem Efficiency issues in evaluating natural stochastic policies due to unknown evaluation policy.
method Derive efficiency bounds for tilting and modified treatment policies, propose nonparametric estimators.
result Proposed estimators attain efficiency bounds under lax conditions and enjoy partial double robustness.
This paper describes an equivalence of the canonical category of N-manifolds of degree 2 with a category of involutive double vector bundles. More precisely, we show how involutive double vector bundles are in duality with double vector bundles endowed with a linear metric. We describe then how special sect…
New algorithm reduces offline RL data requirements significantly.
problem Optimizing policies using only historical data in reinforcement learning.
method Off-Policy Double Variance Reduction (OPDVR) algorithm.
result OPDVR achieves optimal sample complexity with O(H2/dmε2) episodes. Improves DRL for long-term causal inference with semiparametric methods.
problem Efficient inference for policy values in nonparametric MDPs with stringent conditions.
method Semiparametric Double Reinforcement Learning (DRL) with superefficient nonparametric estimators.
result Relaxes overlap conditions and reduces high-dimensional density-ratio estimation.
We provide adaptive inference methods, based on ℓ1 regularization, for regular (semi-parametric) and non-regular (nonparametric) linear functionals of the conditional expectation function. Examples of regular functionals include average treatment effects, policy effects, and derivatives. Examples of non-regular f…
Policy gradient methods achieve linear convergence in simple MDPs.
problem Analyzing convergence rates of policy gradient methods in finite MDPs.
method Connections with policy iteration to show linear convergence with large step-sizes.
result Policy gradient methods succeed with large step-sizes and achieve linear rate of convergence.