online decision-making

Real-Time Approximate Routing for Smart Transit Systems

We study real-time routing policies in smart transit systems, where the platform has a combination of cars and high-capacity vehicles (e.g., buses or shuttles) and seeks to serve a set of incoming trip requests. The platform can use its fleet of cars …

Dynamic Assignment Control of a Closed Queueing Network under Complete Resource Pooling

We study the design of state dependent control for a closed queueing network model, inspired by shared transportation systems such as ridesharing. In particular, we focus on the design of assignment policies, wherein the platform can choose which …

Adaptive Discretization for Model-Based Reinforcement Learning

We introduce the technique of adaptive discretization to design efficient model-based episodic reinforcement learning algorithms in large (potentially continuous) state-action spaces. Our algorithm is based on optimistic one-step value iteration …

Online Allocation and Pricing: Constant Regret via Bellman Inequalities

We develop a framework for designing simple and efficient policies for a family of online allocation and pricing problems, that includes online packing, budget-constrained probing, dynamic pricing, and online contextual bandits with knapsacks. In …

Adaptive Discretization for Episodic Reinforcement Learning in Metric Spaces

We present an efficient algorithm for model-free episodic reinforcement learning on large (potentially continuous) state-action spaces. Our algorithm is based on a novel Q-learning policy with adaptive data-driven discretization. The central idea is …

Predict and Match: Prophet Inequalities with Uncertain Supply

We consider the problem of selling perishable items to a stream of buyers in order to maximize social welfare. A seller starts with a set of identical items, and each arriving buyer wants any one item, and has a valuation drawn i.i.d. from a known …

Uniform Loss Algorithms for Online Stochastic Decision-Making With Applications to Bin Packing

We consider a general class of finite-horizon online decision-making problems, where in each period a controller is presented a stochastic arrival and must choose an action from a set of permissible actions, and the final objective depends only on …

Predict and Match

We consider the problem of selling perishable items to a stream of buyers in order to maximize social welfare. A seller starts with a set of identical items, and each arriving buyer wants any one item, and has a valuation drawn i.i.d. from a known …

From Monetary to Non-Monetary Mechanism Design via Artificial Currencies

Non-monetary mechanisms for repeated allocation and decision-making are gaining widespread use in many real-world settings. Our aim in this work is to study the efficiency and incentive properties of simple mechanisms based on artificial currencies …

The Bayesian Prophet: A Low-Regret Framework for Online Decision Making

We develop a new framework for designing online policies given access to an oracle providing statistical information about an offline benchmark. Having access to such prediction oracles enables simple and natural Bayesian selection policies, and …