arXiv research

Proposes a framework to quantify uncertainty in multi-step decision-making by LLMs.

Paper reduces sample complexity for bilinear systems identification to nearly constant.

Unified framework for multi-view diffusion geometries using intertwined diffusion trajectories.

Recent results in Reinforcement Learning (RL) have shown that agents with limited training environments are susceptible to a large amount of overfitting across many domains. A key challenge for RL generalization is to quantitatively explain the effects of changing parameters on testing performance. Such parameters incl…

Extends RL to random stopping times, improving optimization.

The paper learns particle swarming models from data using Gaussian processes.

Advances in mobile computing technologies have made it possible to monitor and apply data-driven interventions across complex systems in real time. Markov decision processes (MDPs) are the primary model for sequential decision problems with a large or indefinite time horizon. Choosing a representation of the underlying…

Paper tests Markov assumption in sequential decision making.

Develops methods for finding counterfactual explanations in sequential decision making.

Post-processing predictors reduces calibration errors for decision-making.

New algorithm solves uncertain Markov decision processes using Wasserstein uncertainty.

New algorithms detect anomalies in processes with minimal delay.

AI learns to design chemical processes efficiently.

We solve a broad class of sequential decision-making problems with partially observed states.

OSGM uses online learning to adapt stepsize for faster convergence.

Study of bandit problem with Poisson decision times and Lévy processes.

The Chain-of-Decision approach improves forecasting of financial professionals' trading decisions.

New learning process for neural classifiers simplifies decision weights.

Paper presents an algorithm for optimal regret in communicating Markov decision processes.

New method improves decision-making accuracy without complex calculations.

A new model predicts spatio-temporal data using adaptive decision trees and point processes.

Study minimax-optimal rates for offline decision-making with function approximation.

Research in psychology and neuroscience has successfully modeled decision making as a process of noisy evidence accumulation to a decision bound. While there are several variants and implementations of this idea, the majority of these models make use of a noisy accumulation between two absorbing boundaries. A common as…

Gaussian processes adapted for non-Euclidean spaces enhance decision-making.

We address the problem of inverse reinforcement learning in Markov decision processes where the agent is risk-sensitive. In particular, we model risk-sensitivity in a reinforcement learning framework by making use of models of human decision-making having their origins in behavioral psychology, behavioral economics, an…

Develops an actor-critic algorithm for risk-sensitive Markov decision processes.

Study optimality in safety-constrained Markov decision processes using asynchronous value iteration and modified Q-learning.

CPR models complex decision processes by breaking them into context-specific policies, improving interpretability and accuracy.

Risk-controlled post-processing optimizes decision policies under risk constraints.

Overview of risk-sensitive Markov decision processes with Optimized Certainty Equivalent.

GPs' decisions can vary significantly with different kernels, even if kernels are qualitatively similar.

A popular methodology for building binary decision-making classifiers in the presence of imperfect information is to first construct a non-binary "scoring" classifier that is calibrated over all protected groups, and then to post-process this score to obtain a binary decision. We study the feasibility of achieving vari…

A scalable online method for Gaussian processes that improves decision-making in various applications.

Bayesian method infers local rules for collective animal movement.

Introduces DF framework for sampling decisions from target distributions.

Model trains agents to optimize saving and investment strategies for diverse retirement needs.

In Random Forests, proximity distances are a metric representation of data into decision space. By observing how changes in input map to the movement of instances in this space we are able to determine the independent contribution of each feature to the decision-making process. For binary feature vectors, this process …

A new MDP with Bandits approach for sequential decision making in linear-flow scenarios.

Unified framework for human-like decision making in various sequential tasks.

Dynamic probabilistic forecasts guide optimal decisions in uncertain processes.

Algorithm finds safe zones in policy Markov Decision Processes to limit trajectory escape.

This work extends reinforcement learning to handle non-cumulative objectives.

Modeling decision-making dynamics in MDD patients using RL-HMM.

In this paper, we use reinforcement learning to find effective decoding strategies for binary linear codes. We start by reviewing several iterative decoding algorithms that involve a decision-making process at each step, including bit-flipping (BF) decoding, residual belief propagation, and anchor decoding. We then ill…

This work facilitates ensuring fairness of machine learning in the real world by decoupling fairness considerations in compound decisions. In particular, this work studies how fairness propagates through a compound decision-making processes, which we call a pipeline. Prior work in algorithmic fairness only focuses on f…

A new framework designs experiments for better decision-making.

We develop robust Markov Decision Processes with risk measures for uncertain environments.

The paper tackles batch policy learning in Markov Decision Processes, focusing on average reward maximization.