Zobrazeno 1 - 10
of 83
pro vyhledávání: '"Sinclair, Sean A."'
Autor:
Hssaine, Chamsi, Sinclair, Sean R.
We study a censored variant of the data-driven newsvendor problem, where the decision-maker must select an ordering quantity that minimizes expected overage and underage costs based only on offline censored sales data, rather than historical demand r
Externí odkaz:
http://arxiv.org/abs/2412.01763
We study a class of structured Markov Decision Processes (MDPs) known as Exo-MDPs. They are characterized by a partition of the state space into two components: the exogenous states evolve stochastically in a manner not affected by the agent's action
Externí odkaz:
http://arxiv.org/abs/2409.14557
The framework of decision-making, modeled as a Markov Decision Process (MDP), typically assumes a single objective. However, most practical scenarios involve considering tradeoffs between multiple objectives. With that as the motivation, we consider
Externí odkaz:
http://arxiv.org/abs/2408.04488
We consider a practically motivated variant of the canonical online fair allocation problem: a decision-maker has a budget of perishable resources to allocate over a fixed number of rounds. Each round sees a random number of arrivals, and the decisio
Externí odkaz:
http://arxiv.org/abs/2406.02402
Most real-world deployments of bandit algorithms exist somewhere in between the offline and online set-up, where some historical data is available upfront and additional data is collected dynamically online. How best to incorporate historical data to
Externí odkaz:
http://arxiv.org/abs/2210.00025
Autor:
Sinclair, Sean R., Frujeri, Felipe, Cheng, Ching-An, Marshall, Luke, Barbalho, Hugo, Li, Jingling, Neville, Jennifer, Menache, Ishai, Swaminathan, Adith
Many resource management problems require sequential decision-making under uncertainty, where the only uncertainty affecting the decision outcomes are exogenous variables outside the control of the decision-maker. We model these problems as Exo-MDPs
Externí odkaz:
http://arxiv.org/abs/2207.06272
Discretization based approaches to solving online reinforcement learning problems have been studied extensively in practice on applications ranging from resource allocation to cache management. Two major questions in designing discretization-based al
Externí odkaz:
http://arxiv.org/abs/2110.15843
We consider the problem of dividing limited resources to individuals arriving over $T$ rounds. Each round has a random number of individuals arrive, and individuals can be characterized by their type (i.e. preferences over the different resources). A
Externí odkaz:
http://arxiv.org/abs/2105.05308
We consider the problem of dividing limited resources between a set of agents arriving sequentially with unknown (stochastic) utilities. Our goal is to find a fair allocation - one that is simultaneously Pareto-efficient and envy-free. When all utili
Externí odkaz:
http://arxiv.org/abs/2011.14382
We introduce the technique of adaptive discretization to design an efficient model-based episodic reinforcement learning algorithm in large (potentially continuous) state-action spaces. Our algorithm is based on optimistic one-step value iteration ex
Externí odkaz:
http://arxiv.org/abs/2007.00717