Minimal assumptions analysis of Q-learning with time-varying policies.
problem Finite-time analysis of Q-learning with time-varying policies for discounted MDPs.
method Minimal assumptions, Poisson equation decomposition, sensitivity analysis.
result Established convergence rate and sample complexity for Q-learning.
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.
Study online control of unknown time-varying systems with negative and positive results.
problem Online control of time-varying systems with unknown dynamics.
method Algorithmic upper bounds and lower bounds for different policy classes.
result Sublinear adaptive regret bounds for Disturbance Response policies.
The paper provides a non-asymptotic error bound for linear system identification under nonlinear policies.
problem System identification for linear systems with nonlinear and/or time-varying policies under i.i.d. random excitation noises.
method Least square estimation with non-asymptotic error bound for bounded state and action trajectories.
result The error bound is consistent with linear policies and generalizes existing guarantees.
This study evaluates prewar Japanese financial market efficiency using time-varying models.
problem Determining when prewar Japanese financial market lost its price formation function.
method Time-varying parameter model, generalized least squares-based time-varying vector autoregressive model.
result The prewar Japanese financial market lost its price formation function in 1932.
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 TVBO algorithm optimizes time-varying functions with varying sampling frequencies.
problem Optimizing time-varying, expensive, noisy functions with constant frequency assumption.
method Formulated practical recommendations and derived upper regret bound for varying sampling frequencies.
result BOLT algorithm outperforms state-of-the-art TVBO algorithms in experiments.
Paper uses RL to optimize trading in time-varying liquidity markets.
problem Optimal execution in dynamic liquidity markets.
method Double Deep Q-learning for neural networks.
result Trained RL algorithm learns optimal trading policies in time-varying liquidity.
Paper proposes a method for learning and planning in time-varying environments.
problem Learning and planning in unknown, time-varying environments.
method Computes the maximally likely model of the environment using maximum likelihood estimation.
result Generalizes learning algorithms for time-invariant Markov decision processes to time-varying ones.
Study on time-varying APT validity in Japanese stock market.
problem Validity of Arbitrage Pricing Theory (APT) in Japanese stock market over time.
method Rolling window method applied to Fama and MacBeth's two-step regression and Kamstra and Shi's generalized GRS test.
result APT validity is unstable over time in Japanese stock market, influenced by monetary policy and business cycle.
New algorithm minimizes worst-case regret in uncertain, time-varying dynamics.
problem Model-based policy learning in uncertain, time-varying dynamics.
method Planning regret metric and iterative algorithm for minimizing it.
result Empirical evidence shows the proposed algorithm outperforms existing methods.
The paper tackles revenue management with time-varying demand using posterior sampling.
problem Maximizing revenue in real-time applications with unknown and time-varying demand.
method Episodic generalization of RM problem, posterior sampling algorithm for linear programming optimization.
result The proposed algorithm outperforms other methods and is comparable to the optimal policy in hindsight.
Develops framework for estimating and improving DTRs with time-varying IV in the presence of unmeasured confounding.
problem Estimating DTRs from observational data with unmeasured confounding.
method Time-varying instrumental variable (IV) framework for estimating and improving DTRs.
result IV-optimal and IV-improved DTRs perform better than DTRs assuming no unmeasured confounding.
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-…
This paper proposes a parsimoniously time varying parameter vector autoregressive model (with exogenous variables, VARX) and studies the properties of the Lasso and adaptive Lasso as estimators of this model. The parameters of the model are assumed to follow parsimonious random walks, where parsimony stems from the ass…
New framework detects time-varying economic persistence.
problem Time-varying persistence in economic shocks.
method Localized regression techniques to identify evolving heterogeneity.
result Substantial persistence variations align with macroeconomic events.
Time-varying parameters are shown to be ridge regressions, simplifying computations and tuning.
problem Capturing structural change in economic data.
method Ridge regression approach, including cross-validation for tuning, and extensions for sparsity and reduced-rank restrictions.
result The method efficiently estimates large numbers of time-varying parameters, demonstrated with Canadian monetary policy data.
Study analyzes GDP growth of CEE countries using time-varying coefficients.
problem Understanding GDP growth patterns of CEE countries post-integration.
method Panel regression with time-varying coefficients.
result Private debt plays a crucial role in economic growth.
We investigate the relationship between market efficiency of rice futures transaction in Osaka and the Japanese government intervention in rice distributions by directly buying and selling rice during the interwar period, from the middle 1910s to 1939, considering the context of "discretion versus rules." We use a time…
Study examines time-varying betas and their volatility in bank interest income and expense margins.
problem Understanding the variability of bank betas and their impact on net interest margins.
method Used state-space methods to estimate time-varying betas and conditional volatility.
result Substantial variation in interest income and expense betas, leading to varying net interest margin coefficients.
Adaptive optimal control using value iteration initiated from a stabilizing control policy is theoretically analyzed in terms of stability of the system during the learning stage without ignoring the effects of approximation errors. This analysis includes the system operated using any single/constant resulting control …
This paper solves optimal consumption-investment problems with time-varying preferences.
problem Optimal consumption-investment problems under time-varying incomplete preferences.
method Develops a martingale-type solution in a topological vector space, using stochastic processes and scalarization methods.
result Optimal investment policies are set-valued, with selectors decomposed into four components.
New algorithm reduces control error in systems with changing dynamics.
problem Online control of systems with time-varying linear dynamics.
method Introduces adaptive regret metric and a novel meta-algorithm.
result First adaptive regret bound for online convex optimization with memory.
Typically, operational risk losses are reported above a threshold. Fitting data reported above a constant threshold is a well known and studied problem. However, in practice, the losses are scaled for business and other factors before the fitting and thus the threshold is varying across the scaled data sample. A report…
Enhances FAVAR models with autoencoder for better economic forecasting and interpretability.
problem Limitations of linear FAVAR models in forecasting and structural analysis.
method Introduces Grouped Sparse autoencoder with time-varying parameters.
result The Grouped Sparse autoencoder produces more interpretable factors and superior forecasting performance.
A new method for steering large agent populations efficiently.
problem Controlling the configuration of a swarm of identical, interacting cooperative agents.
method Mean-Field Schrodinger Bridges with Gaussian Mixture Models.
result A highly efficient parameterization to approximate optimal solutions of the MFSB problem in closed form.
Study minimax rates for online learning with time-varying dynamics.
problem Online learning with time-varying state and cost dynamics.
method Non-constructive upper and lower bounds, complexity and stability terms.
result Characterization of minimax rates and necessary conditions for learnability.
Adaptive optimal control using value iteration (VI) initiated from a stabilizing policy is theoretically analyzed in various aspects including the continuity of the result, the stability of the system operated using any single/constant resulting control policy, the stability of the system operated using the evolving/ti…
Greedy policies perform poorly in imperfectly observed contextual bandits.
problem Performance of Greedy policies in bandits with partially observed contexts.
method Analysis of Greedy reinforcement learning policies under imperfectly observed contextual bandits.
result Worst-case regret grows poly-logarithmically with the time horizon and the failure probability.
New framework for dynamic causal graph modeling and effect estimation.
problem Dynamic changes in causal relationships over time.
method Score-based causal discovery with autoregressive model structure.
result Dynamic causal graph with time-varying causal relations.
This paper examines the integration process of the Japanese major rice markets (Tokyo and Osaka) from 1881 to 1932. Using a non-Bayesian time-varying vector error correction model, we argue that the process strongly depended on the government's policy on the network system of the telegram and telephone; rice traders wi…
Tabular Q-learning outperforms advanced RL methods in monetary policy.
problem Dynamic setting of short-term interest rates to stabilize inflation and unemployment under uncertain macroeconomic conditions.
method Discrete-action Markov Decision Process with tabular Q-learning, SARSA, Actor-Critic, Deep Q-Networks, Bayesian Q-learning, POMDP formulations.
result Standard tabular Q-learning achieved the best performance (-615.13 +- 309.58 mean return) compared to advanced RL methods and traditional policy rules.
Thompson Sampling reduces regret in non-episodic restless bandits.
problem Learning optimal policies in time-varying reward systems.
method Variant of Thompson Sampling applied to infinite horizon restless bandits.
result Sub-linear regret bound of O ( T log T ) O(\sqrt{T}\log T) O ( T log T ) proved for non-episodic case. Paper uses RL to optimize multi-asset portfolios in fluctuating markets.
problem Optimizing multi-asset portfolios in time-varying financial markets.
method Soft Actor-Critic (SAC) algorithm for policy learning, policy iteration process.
result SAC algorithm outperforms in various criteria in simulated and real financial markets.
Study examines how industrial emissions evolve over time in response to various factors.
problem Understanding how firm-level emissions change over time in response to environmental regulation, economic conditions, and organizational constraints.
method Used a time-varying mean-group estimator to link emissions data with firm characteristics and macroeconomic indicators over 1992-2023.
result Firm-level characteristics and aggregate conditions have different impacts on emissions growth at different times.
New RL algorithm tackles non-stationary environments with flexible policy updates.
problem Non-stationary reinforcement learning with time-varying rewards and transition probabilities.
method Model-free policy-based algorithm NS-NAC with restart-based exploration and dynamic learning rates.
result Dynamic regret of i l d e O ( ∣ S ∣ 1 / 2 ∣ A ∣ 1 / 2 Δ T 1 / 6 T 5 / 6 ) ilde{\mathscr O}(|S|^{1/2}|A|^{1/2}Δ_T^{1/6}T^{5/6}) i l d e O ( ∣ S ∣ 1/2 ∣ A ∣ 1/2 Δ T 1/6 T 5/6 ) for both algorithms. Estimates RL data for dynamic treatment effects using GMM.
problem Estimating dynamic treatment effects from RL data with nonstationary behavior policies.
method Weighted GMM approach to stabilize variance in adaptive RL settings.
result Valid hypothesis testing and confidence regions for dynamic treatment effects.
SARSA is an on-policy algorithm to learn a Markov decision process policy in reinforcement learning. We investigate the SARSA algorithm with linear function approximation under the non-i.i.d.\ data, where a single sample trajectory is available. With a Lipschitz continuous policy improvement operator that is smooth eno…
New algorithms for collaborative reinforcement learning with limited communication.
problem Efficiently learning value functions in multi-agent systems with strict information constraints.
method Distributed gradient-based temporal difference algorithms with consensus schemes.
result Parameter estimates converge to ODEs with defined invariant sets under general assumptions.
Simulation framework assesses ROI of chronic disease adherence and policy timing.
problem Uncertainty in ROI of adherence-enhancing interventions under heterogeneous patient behavior and socioeconomic variation.
method Simulation-based framework integrating disease progression, time-varying adherence, and policy timing.
result Early and adaptive interventions yield highest ROI, exceeding 20% under certain conditions.
The paper tackles non-stationary MAB with periodic rewards.
problem Non-stationary mean rewards over time in a business context.
method Combines Fourier analysis with confidence-bound learning to estimate periods and minimize regret.
result Proposes a near-optimal policy with a regret bound of O ( T ∑ k = 1 K T k ) O(\sqrt{T\sum_{k=1}^K T_k}) O ( T ∑ k = 1 K T k ) . Extends tracking guarantees for time-varying variational inequalities.
problem Tracking solutions of time-varying variational inequalities.
method Extends existing results to sublinear solution paths and periodic problems.
result Discrete dynamical systems of periodic time-varying VI can exhibit chaotic behavior or converge to the solution.
New method tracks time-varying parameters in data.
problem Tracking unknown time-varying parameters in data.
method Stochastic gradient descent-based recursive scheme with log-likelihood as gain function.
result Convergence in mean-square error in a suitable neighborhood of the unknown parameter.
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.
Evaluating AI investment strategies
problem Auditing a black-box algorithmic decision-maker
method Exact decomposition of cumulative regret
result Cumulative regret equals sum of per-period covariances
Adaptive OMD reduces variance in learning optimal strategies for imperfect information games.
problem High variance in learning optimal strategies for imperfect information games.
method Fixed sampling approach with locally applied Online Mirror Descent (OMD) algorithm.
result Convergence rate of i l d e O ( T − 1 / 2 ) ilde{\mathcal{O}}(T^{-1/2}) i l d e O ( T − 1/2 ) with high probability. In this article we solve the problem of maximizing the expected utility of future consumption and terminal wealth to determine the optimal pension or life-cycle fund strategy for a cohort of pension fund investors. The setup is strongly related to a DC pension plan where additionally (individual) consumption is taken i…
DeepBlip estimates treatment effects over time using neural networks.
problem Estimating treatment effects over time with interpretable blip effects.
method DeepBlip uses a novel double optimization trick to enable simultaneous learning of blip functions with sequential neural networks.
result DeepBlip achieves state-of-the-art performance across various clinical datasets.