2 papers
cs.GT2024
Disrupting Bipartite Trading Networks: Matching for Revenue Maximization
Luca D'Amico-Wong, Yannai A. Gonczarowski, Gary Qiurui Ma +1
We model the role of an online platform disrupting a market with unit-demand buyers and unit-supply sellers. Each seller can transact with a subset of the buyers whom she already k…
cs.LG2024
Easy as ABCs: Unifying Boltzmann Q-Learning and Counterfactual Regret Minimization
Luca D'Amico-Wong, Hugh Zhang, Marc Lanctot +1
We propose ABCs (Adaptive Branching through Child stationarity), a best-of-both-worlds algorithm combining Boltzmann Q-learning (BQL), a classic reinforcement learning algorithm fo…