Proposes a new decision rule for continuous treatments.
problem Developing personalized treatment recommendations for continuous treatments.
method Jump interval-learning method to estimate conditional mean of outcomes.
result Optimal interval-valued decision rule (I2DR) for continuous treatments.
Paper solves POMDPs in continuous time and discrete spaces.
problem Optimal decision making in discrete state and action space systems under partial observability.
method Combining optimal filtering theory and deep learning to solve a Hamilton-Jacobi-Bellman equation.
result Derives a mathematical description and solution approach for continuous-time POMDPs.
We present the first PAC optimal algorithm for Bayes-Adaptive Markov Decision Processes (BAMDPs) in continuous state and action spaces, to the best of our knowledge. The BAMDP framework elegantly addresses model uncertainty by incorporating Bayesian belief updates into long-term expected return. However, computing an e…
We show that for neural network functions that have width less or equal to the input dimension all connected components of decision regions are unbounded. The result holds for continuous and strictly monotonic activation functions as well as for the ReLU activation function. This complements recent results on approxima…
New techniques optimize decision trees for interpretable machine learning.
problem Optimizing decision trees for interpretable machine learning.
method General framework for decision tree optimization addressing imbalanced data and continuous variables.
result Proves optimal decision trees for various objectives.
Stochastic domains often involve risk-averse decision makers. While recent work has focused on how to model risk in Markov decision processes using risk measures, it has not addressed the problem of solving large risk-averse formulations. In this paper, we propose and analyze a new method for solving large risk-averse …
In order to simulate the complex phenomena manifested in stock markets, we introduce a continuous asynchronous model in which millions of individual traders interact through a central orders matching mechanism, just as it happens in real stock markets. Each trader has a unique decision function, which allows him/ her t…
New framework optimizes decisions under uncertainty considering causal and continuous data.
problem Optimizing decisions under uncertain distributions with causal and continuous data structures.
method Developed a framework using Causal Sinkhorn DRO with Soft Regression Forest decision rules.
result Framework provides interpretable and tractable decision rules for optimizing under uncertainty.
A new approach for specifying and synthesizing subroutines for optimizing metrics.
problem Specifying and optimizing subroutines for various metrics.
method Formalizing programming by rewards (PBR), using continuous-optimization techniques to synthesize decision functions as if-then-else programs.
result Synthesized decision functions are optimal in cases when rewards have nice properties.
We present SplineNets, a practical and novel approach for using conditioning in convolutional neural networks (CNNs). SplineNets are continuous generalizations of neural decision graphs, and they can dramatically reduce runtime complexity and computation costs of CNNs, while maintaining or even increasing accuracy. Fun…
New model accounts for continuous human trajectories in robotics.
problem Inaccurate probabilistic models of human behavior in robotics.
method Developed a new probabilistic model that considers distances between continuous trajectories.
result The new model outperforms existing models in explaining human behavior and improving robot inference.
Study of bandit problem with Poisson decision times and Lévy processes.
problem Continuous-time multi-armed bandit problem with Poisson decision times.
method Gittins index policy applied to spectrally one-sided Lévy processes.
result Gittins index converges to classical Lévy bandit index.
DQNs can approximate optimal Q-functions with high accuracy on compact sets.
problem Approximating optimal Q-functions in continuous-time Markov Decision Processes.
method Stochastic control, FBSDEs, residual network approximation theorems, large deviation bounds, viscosity solutions.
result DQNs can approximate optimal Q-functions on compact sets with arbitrary accuracy and high probability.
We study the Combinatorial Pure Exploration problem with Continuous and Separable reward functions (CPE-CS) in the stochastic multi-armed bandit setting. In a CPE-CS instance, we are given several stochastic arms with unknown distributions, as well as a collection of possible decisions. Each decision has a reward accor…
Study minimax rates for binary classifier estimation with margin conditions.
problem Estimating binary classifiers with geometric margin conditions.
method Derive lower bounds for worst-case learning rates over various function classes.
result Identify optimal rates close to O(n−1) for different function classes. New method learns binary decision trees efficiently.
problem Learning binary decision trees for data partitioning.
method Argmin differentiation for discrete and continuous parameters.
result Produces competitive binary trees with fast training.
Introduces DF framework for sampling decisions from target distributions.
problem Sampling from target distributions with additional guidance.
method DF framework based on MDP and Path Integral Diffusion.
result DF enhances guided sampling across various applications.
A new method for learning distance metrics for K-NN classification.
problem Improving the performance of K-NN classifier by learning an appropriate distance metric.
method Designing a continuous decision function for K-NN and minimizing its continuous empirical risk function.
result The proposed ANN algorithm outperforms existing methods like LMNN, NCA, and pairwise constraints.
Novel framework proves fast RL convergence in continuous spaces.
problem Analyzing stability in continuous state-action RL.
method Introduces a novel framework to analyze stability properties of RL.
result Highlights two key stability properties and demonstrates their satisfaction in RL.
SupRB learns rules for continuous decision problems from examples.
problem Learning from continuous choices and explaining decisions to operators.
method SupRB is a supervised rule-based learning system for multi-dimensional continuous problems.
result SupRB provides human-understandable rules for optimal choices and quality predictions.
Deep neural networks achieve optimal learning rates for high-dimensional classification.
problem Learning classification functions from noisy data with smooth boundaries.
method Empirical risk minimization over deep neural networks for locally Barron-regular decision boundaries.
result Optimal estimation rates are independent of dimension and can be achieved by deep neural networks.
Decision trees are consistent for regression and classification tasks even with many predictors.
problem Consistency of decision trees with many predictors.
method CART and C4.5 methodology, oracle inequality, sparsity constraints.
result Decision trees and random forests are consistent for various types of data.
New method extends low-rank MDPs to continuous action spaces.
problem Limited applicability of current low-rank MDP methods to continuous action spaces.
method Extending FLAMBE algorithm to continuous action spaces with Hölder smoothness conditions.
result Similar PAC bound achieved for continuous actions with polynomial dependence on smoothness order.
The paper tackles finding optimal treatment sequences in continuous state spaces.
problem Finding counterfactually optimal action sequences in continuous state spaces.
method Formalizes the problem using finite horizon Markov decision processes and structural causal models. Develops a search method based on the A* algorithm.
result The method can find optimal action sequences in polynomial time under certain conditions.
We learn sensor trees from training data to minimize sensor acquisition costs during test time. Our system adaptively selects sensors at each stage if necessary to make a confident classification. We pose the problem as empirical risk minimization over the choice of trees and node decision rules. We decompose the probl…
New RL framework models continuous-time dynamics using neural ODEs.
problem Modeling continuous-time dynamics in semi-Markov decision processes.
method Model-based reinforcement learning with neural ODEs.
result High-performing policies developed with minimal data.
Develops a statistical learning framework for personalized asset allocation.
problem Continuous-action decision-making with a large number of characteristics.
method Discretization approach with generalized penalties for penalized regression.
result Improves financial well-being with individualized optimal asset allocation.
New method for RL tasks transfer using Lipschitz continuity.
problem Knowledge transfer in RL tasks over time.
method Established Lipschitz continuity between MDPs and applied it to RL.
result Improved convergence rate and no negative transfer with high probability.
Inverse optimal control, also known as inverse reinforcement learning, is the problem of recovering an unknown reward function in a Markov decision process from expert demonstrations of the optimal policy. We introduce a probabilistic inverse optimal control algorithm that scales gracefully with task dimensionality, an…
New method optimizes decision-making in uncertain environments.
problem Optimal decision-making under partial observability.
method Nested sequential Monte Carlo algorithm for continuous POMDPs.
result Demonstrated effectiveness on continuous POMDP benchmarks.
Bayesian decision theory outlines a rigorous framework for making optimal decisions based on maximizing expected utility over a model posterior. However, practitioners often do not have access to the full posterior and resort to approximate inference strategies. In such cases, taking the eventual decision-making task i…
Proposes a new method to estimate continuous treatment policies and match treatments effectively.
problem Current methods struggle with continuous treatment policies and complex matching.
method Formulates treatment effectiveness as a parametrizable model, using deep learning for optimization.
result Significant improvement in treatment effectiveness and matching efficiency.
A new RL framework for risk-sensitive decision-making using convex scoring functions.
problem Time-inconsistent risk measures in reinforcement learning.
method Convex scoring functions, augmented state space, auxiliary variable, customized Actor-Critic algorithm.
result Theoretical guarantees for approximation and convergence under certain conditions.
Study on inventory management under uncertainty using smooth ambiguity preference.
problem Managing inventory under Knightian uncertainty with smooth ambiguity preference.
method Demonstrates continuous-time smooth ambiguity as the infinitesimal limit of Kalman-Bucy filtering with recursive robust utility. Solves forward-backward stochastic differential equations with quadratic growth to determine cost function. Derives value function and optimal control policy using variational inequalities and viscosity solutions. Transforms problem into two-dimensional singular control.
result Ambiguity drives decision-makers to act earlier, reducing the continuation region.
New RL approach handles non-exponential discounting for sequential decisions.
problem Modeling human discounting in sequential decision-making tasks.
method Generalized model-based reinforcement learning with arbitrary discount functions, using Hamilton-Jacobi-Bellman equation and collocation method.
result Validated approach on simulated problems, showing applicability to human discounting.
We seek to learn an effective policy for a Markov Decision Process (MDP) with continuous states via Q-Learning. Given a set of basis functions over state action pairs we search for a corresponding set of linear weights that minimizes the mean Bellman residual. Our algorithm uses a Kalman filter model to estimate those …
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.
Proposes a method for generating prediction intervals in dose-response models using conformal prediction.
problem Uncertainty quantification in continuous treatments for personalized healthcare decisions.
method Causal dose-response problem framed as covariate shift, using weighted conformal prediction with propensity estimation and kernel functions.
result Demonstrates the significance of covariate shift assumptions for robust prediction intervals.
SMART combines decision trees and MARS for better regression modeling.
problem High variance in decision trees for continuous relationships, poor performance in MARS for discontinuities.
method SMART uses a decision tree to identify subsets with distinct continuous relationships, then applies MARS to fit these relationships independently.
result SMART improves regression performance over state-of-the-art methods in capturing discontinuities and continuous relationships.
Survival MDN uses invertible functions to speed up survival analysis models.
problem Training neural ODEs for survival analysis is computationally expensive.
method Survival MDN applies an invertible positive function to MDN outputs.
result Survival MDN outperforms or matches other models on concordance, Brier score, and log-likelihood.
We consider the optimization of an uncertain objective over continuous and multi-dimensional decision spaces in problems in which we are only provided with observational data. We propose a novel algorithmic framework that is tractable, asymptotically consistent, and superior to comparable methods on example problems. O…
New PG losses improve decision optimization in misspecified models.
problem Improving decision optimization in models that are not perfectly specified.
method Introducing Perturbation Gradient (PG) losses to connect decision loss with directional derivatives and optimizing using gradient techniques.
result PG losses yield best-in-class policies asymptotically, even in misspecified settings.
This research introduces an autonomous robot navigation method using reinforcement learning.
problem Improving robot navigation in complex environments.
method Deep Q Network (DQN) and Proximal Policy Optimization (PPO) models for path planning and decision-making.
result The models enhance robot navigation ability and adaptive learning in unknown environments.
New algorithm reduces regret in online learning for piecewise continuous functions.
problem Exponential loss in efficiency when moving from classical to adversarial learning.
method Introduces generalized bracketing numbers and Follow-the-Perturbed-Leader algorithm.
result Optimal scaling of optimization oracle calls with average regret.
We consider Markov Decision Problems defined over continuous state and action spaces, where an autonomous agent seeks to learn a map from its states to actions so as to maximize its long-term discounted accumulation of rewards. We address this problem by considering Bellman's optimality equation defined over action-val…
A new meta-learner improves prediction of individualized outcomes in sequential decisions.
problem Predicting individualized outcomes over long horizons in sequential decision-making.
method Developed a novel meta-learner called DRQ-learner with theoretical guarantees of orthogonality and quasi-oracle efficiency.
result DRQ-learner achieves quasi-oracle efficiency, doubly robustness, and Neyman-orthogonality.
POWSS simplifies Q-value estimation in POMDPs with continuous observations.
problem Lack of theoretical justification for online sampling-based algorithms in POMDPs with continuous observation spaces.
method Developed POWSS, a simplified algorithm that estimates Q-values accurately with high probability and can approach optimality with increased computational power.
result POWSS provides formal theoretical guarantees for Q-value estimation in POMDPs with continuous observations.
Study optimal periodic dividend strategies for risky businesses with transaction costs.
problem Optimal periodic dividend strategies for spectrally positive Lévy risk processes with fixed transaction costs.
method Investigates periodic (bu,bl) strategies for a Poisson arrival process of decision times. result A periodic (bu,bl) strategy is optimal with lump sum dividends net of transaction costs.