2 papers
cs.GT2026
Randomly Wrong Signals: Bayesian Auction Design with ML Predictions
Ilan Lobel, Humberto Moreira, Omar Mouchtaki
We study auction design when a seller relies on machine-learning predictions of bidders' valuations that may be unreliable. Motivated by modern ML systems that are often accurate b…
stat.ML2025
Reinforcement Learning in MDPs with Information-Ordered Policies
Zhongjun Zhang, Shipra Agrawal, Ilan Lobel +2
We propose an epoch-based reinforcement learning algorithm for infinite-horizon average-cost Markov decision processes (MDPs) that leverages a partial order over a policy class. In…