8 citations · 20 across the 10 of their papers we have counts for
11 papers
A Unified Optimism-Agnostic Framework for Linear Bandits over Spherical Action Sets
Arda Güçlü, Subhonmesh Bose, John R. Birge
Linear bandits model sequential decision-making problems with noisy rewards that are linear in the decision variable, where an agent must simultaneously learn about an unknown para…
On the Convergence of L-shaped Algorithms for Two-Stage Stochastic Programming
John R. Birge, Haihao Lu, Baoyu Zhou
In this paper, we design, analyze, and implement a variant of the two-loop L-shaped algorithms for solving two-stage stochastic programming problems that arise from important appli…
Quantification of Market Power Mitigation via Efficient Aggregation of Distributed Energy Resources
Zuguang Gao, Khaled Alshehri, John R. Birge
Distributed energy resources (DERs) such as solar panels have small supply capacities and cannot be directly integrated into wholesale markets. So, the presence of an intermediary…
Learning from Stochastically Revealed Preference
John R. Birge, Xiaocheng Li, Chunlin Sun
We study the learning problem of revealed preference in a stochastic setting: a learner observes the utility-maximizing actions of a set of agents whose utility follows some unknow…
Finite-Sample Analysis of Decentralized Q-Learning for Stochastic Games
Zuguang Gao, Qianqian Ma, Tamer Başar +1
Learning in stochastic games is arguably the most standard and fundamental setting in multi-agent reinforcement learning (MARL). In this paper, we consider decentralized MARL in st…
Approximation Schemes for Multiperiod Binary Knapsack Problems
Zuguang Gao, John R. Birge, Varun Gupta
An instance of the multiperiod binary knapsack problem (MPBKP) is given by a horizon length , a non-decreasing vector of knapsack sizes where denotes…