相关论文: Analysis and Evaluation of Baseline Manipulation i…

Approximate dynamic programming is a popular method for solving large Markov decision processes. This paper describes a new class of approximate dynamic programming (ADP) methods- distributionally robust ADP-that address the curse of…

This study investigates real-time assignment decisions for extraboard transit operators, who are responsible for covering open work due to unexpected events such as driver absenteeism. Efficient usage of extraboard operators is critical as…

We study the sample complexity of the plug-in approach for learning $\varepsilon$-optimal policies in average-reward Markov decision processes (MDPs) with a generative model. The plug-in approach constructs a model estimate then computes an…

We consider the problem of controlling a Markov decision process (MDP) with a large state space, so as to minimize average cost. Since it is intractable to compete with the optimal policy for large scale problems, we pursue the more modest…

Demand response (DR) is becoming increasingly important as the volatility on the grid continues to increase. Current DR approaches are completely manual and rule-based or involve deriving first principles based models which are extremely…

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…

Rollout algorithms have demonstrated excellent performance on a variety of dynamic and discrete optimization problems. Interpreted as an approximate dynamic programming algorithm, a rollout algorithm estimates the value-to-go at each…

This paper proposes a multi-day needs-based model for activity and travel demand analysis. The model captures the multi-day dynamics in activity generation, which enables the modeling of activities with increased flexibility in time and…

Rising provider turnover results in frequently needing to rematch patients with available providers. However, the rematching process is cumbersome for both patients and health systems, resulting in labor-intensive and ad hoc reassignments.…

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

Machine Learning (ML) research has increased substantially in recent years, due to the success of predictive modeling across diverse application domains. However, well-known barriers exist when attempting to deploy ML models in high-stakes,…

Bayesian Neural Networks (BNN) have recently emerged in the Deep Learning world for dealing with uncertainty estimation in classification tasks, and are used in many application domains such as astrophysics, autonomous driving...BNN assume…

In mobile edge computing systems, base stations (BSs) equipped with edge servers can provide computing services to users to reduce their task execution time. However, there is always a conflict of interest between the BS and users. The BS…

This note re-visits the rolling-horizon control approach to the problem of a Markov decision process (MDP) with infinite-horizon discounted expected reward criterion. Distinguished from the classical value-iteration approach, we develop an…

Demand-side management presents significant benefits in reducing the energy load in smart grids by balancing consumption demands or including energy generation and/or storage devices in the user's side. These techniques coordinate the…

Due to the emergence of new technologies, the whole electricity system is undergoing transformations on a scale and pace never observed before. The decentralization of energy resources and the smart grid have forced utility services to…

We study the joint scheduling of behind-the-meter distributed energy resources (DERs), including flexible loads, renewable generation, and battery energy storage systems, under net energy metering tariffs with demand charges. The problem is…

Decision-making under distribution shift is a central challenge in reinforcement learning (RL), where training and deployment environments differ. We study this problem through the lens of robust Markov decision processes (RMDPs), which…

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for post-training large reasoning models (LRMs) using policy-gradient methods such as GRPO. To stabilize training, these methods typically center…

An important problem in training deep networks with high capacity is to ensure that the trained network works well when presented with new inputs outside the training dataset. Dropout is an effective regularization technique to boost the…